© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 33-TRANSCODER-HP
    7. 52562
    Prev
    Next
    INDEX
    Explanations

    speak/talk

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    out
    -0.30
    ou
    -0.29
    where
    -0.28
    .
    -0.28
     gang
    -0.28
    !
    -0.28
    ..
    -0.27
    vers
    -0.26
    ...
    -0.26
     quadr
    -0.26
    POSITIVE LOGITS
    edly
    0.29
    åı¦è¡Į
    0.27
    tml
    0.26
    ä½ľåĵģåĨħ容
    0.26
     Pharmaceuticals
    0.26
    atel
    0.25
    Donate
    0.25
    xbd
    0.25
     mee
    0.25
    对åħ¬åı¸
    0.25
    Activations Density 0.021%

    No Known Activations