© 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. 19-TRANSCODER-HP
    7. 7804
    Prev
    Next
    INDEX
    Explanations

    programming code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_19.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.19.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     stag
    -0.29
    åĬŁ
    -0.29
    çľĭå®Į
    -0.26
     Hamm
    -0.24
    ç¬ijäºĨç¬ij
    -0.23
    ToShow
    -0.23
    amm
    -0.23
    çļĦ帮åĬ©ä¸ĭ
    -0.23
    tested
    -0.23
     pitches
    -0.23
    POSITIVE LOGITS
    ogh
    0.27
    orate
    0.26
    å·¥åľ°
    0.26
    éĿ¢ç§¯çº¦
    0.25
     Pearce
    0.25
    @endforeach
    0.24
    æĶ¹èī¯
    0.24
    æ¹ĸ
    0.24
    éli
    0.24
    ophile
    0.24
    Activations Density 0.089%

    No Known Activations