© 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. 23-TRANSCODER-HP
    7. 23831
    Prev
    Next
    INDEX
    Explanations

    Conversational text

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    è¿ĻäºĽéĹ®é¢ĺ
    -0.29
    ayload
    -0.28
    ä¸įåĪ°
    -0.28
    enery
    -0.27
    ä»Ģä¹Īä¸ľè¥¿
    -0.26
    likely
    -0.26
    è§ĦåĪĴ建设
    -0.26
    /rem
    -0.25
     seks
    -0.25
    lessly
    -0.25
    POSITIVE LOGITS
    è¿Ļæł·
    0.28
    GBT
    0.28
    æĽ´éĩįè¦ģ
    0.28
    abd
    0.27
    æıIJé«ĺ
    0.26
    VT
    0.25
    RT
    0.25
    æī¾åĪ°äºĨ
    0.25
    æīĢ说
    0.24
     thinking
    0.24
    Activations Density 0.001%

    No Known Activations