© 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. 30-TRANSCODER-HP
    7. 96715
    Prev
    Next
    INDEX
    Explanations

    who

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Where
    -0.31
     Where
    -0.29
    主人
    -0.29
    arian
    -0.28
    ä»Ģ麽
    -0.27
     privile
    -0.27
    WHERE
    -0.27
    çļĦéĤ£ä¸Ģ
    -0.25
    eme
    -0.25
    where
    -0.25
    POSITIVE LOGITS
     who
    1.23
    who
    1.03
    è°ģ
    1.00
     Who
    0.94
    Who
    0.89
    è°ģèĥ½
    0.80
    誰
    0.80
     whom
    0.79
     whose
    0.75
     qui
    0.73
    Activations Density 0.884%

    No Known Activations