© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 130065
    Prev
    Next
    INDEX
    Explanations

    Period

    np_max-act · gemini-2.0-flash

    periods at the end of answer statements in Q&A formatting (. after a declarative response to a question).

    oai_token-act-pair · deepseek-v3Triggered by @finnwit
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æĦıæĢĿ
    -0.27
    åįģåĪĨéĴŁ
    -0.27
    åĽ¾ä¸º
    -0.25
    èIJ¥åĪ©
    -0.25
     ay
    -0.25
     wards
    -0.24
    æħ®
    -0.24
     ContentView
    -0.24
     definition
    -0.23
    .ndarray
    -0.23
    POSITIVE LOGITS
    playing
    0.28
    æ±ŁåĮĹ
    0.25
    æľīä¸ĢäºĽ
    0.25
    uts
    0.25
    ä¹Łæĺ¯éĿŀ常
    0.25
    èĩ³äºİ
    0.25
    æѤåĪ»
    0.24
    ä¹ŁéĿŀ常
    0.24
    ä¸Ĭç½ij
    0.24
    prus
    0.24
    Activations Density 0.008%

    No Known Activations