© 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. 129471
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    èįª
    -0.28
    ç¾½
    -0.26
     unspecified
    -0.25
    OfYear
    -0.25
    IBUT
    -0.25
    emma
    -0.24
    æĿijåħļæĶ¯éĥ¨
    -0.24
    ees
    -0.24
    主è§Ĥ
    -0.23
     subdivision
    -0.23
    POSITIVE LOGITS
    pered
    0.31
    第ä¸Ģ家
    0.28
    tributes
    0.26
    _rev
    0.26
    ä¹Łæĺ¯å¦ĤæѤ
    0.26
    igner
    0.25
    cus
    0.25
    ıp
    0.25
    åĻ¤
    0.24
    pNet
    0.24
    Activations Density 17.072%

    No Known Activations

    This feature has no known activations.