© 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. 20-TRANSCODER-HP
    7. 63767
    Prev
    Next
    INDEX
    Explanations

    per

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     reconc
    -0.27
    utor
    -0.26
    åħ¬å®īéĥ¨
    -0.25
    å°ĨåĨĽ
    -0.25
    ppe
    -0.25
    æ®Ľ
    -0.24
    åĪ©
    -0.24
    ille
    -0.24
    çijķ
    -0.24
     Sidebar
    -0.24
    POSITIVE LOGITS
    纵åIJij
    0.26
    涩
    0.26
    endale
    0.25
    ãģĪãĤĭ
    0.24
    classList
    0.24
    priv
    0.24
    erset
    0.24
    èĴĤ
    0.24
    chap
    0.24
    éĶ²
    0.24
    Activations Density 6.034%

    No Known Activations