© 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. 63360
    Prev
    Next
    INDEX
    Explanations

    in

    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
    èĦĨå¼±
    -0.27
    微信
    -0.26
    ä¾µ
    -0.26
    ingly
    -0.24
    gos
    -0.24
    主è¦ģåİŁåĽł
    -0.24
     Opening
    -0.24
    osed
    -0.23
    å½±åĵį
    -0.23
    åı¯æݧ
    -0.23
    POSITIVE LOGITS
    åĽ´
    0.27
    belt
    0.27
    itia
    0.26
    -online
    0.25
    offline
    0.25
     offline
    0.25
     dear
    0.24
    åIJĽåŃIJ
    0.24
    trinsic
    0.24
    èĤĸ
    0.24
    Activations Density 0.171%

    No Known Activations