© 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. 25-TRANSCODER-HP
    7. 109581
    Prev
    Next
    INDEX
    Explanations

    Amounts and numbers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     \"%
    -0.29
    æĦıåĽ¾
    -0.27
     Gratuit
    -0.26
    —that
    -0.25
     Guess
    -0.25
    okit
    -0.25
     '//
    -0.25
    ;m
    -0.25
    ãģĻãģ¹ãģį
    -0.24
     personalize
    -0.24
    POSITIVE LOGITS
    IVO
    0.29
     blocker
    0.28
    ored
    0.28
    .pub
    0.27
     increased
    0.26
    ubar
    0.26
    大åĬĽåıijå±ķ
    0.26
     regulated
    0.25
    å±ĭ顶
    0.25
     stronger
    0.25
    Activations Density 0.906%

    No Known Activations