© 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. 27-TRANSCODER-HP
    7. 56443
    Prev
    Next
    INDEX
    Explanations

    9

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     ex
    -0.29
     cat
    -0.26
    eld
    -0.26
     domain
    -0.26
    æĦķ
    -0.26
    çĻ½é¢Ĩ
    -0.26
     pairwise
    -0.25
    æĥŃ
    -0.25
    ex
    -0.24
    _categoria
    -0.24
    POSITIVE LOGITS
    æĻ®éģįåŃĺåľ¨
    0.30
    æĻ®éģį
    0.28
    è£ķ
    0.27
    getMessage
    0.27
     Woodward
    0.26
    å·¡è§Ĩ
    0.26
    grown
    0.25
    uste
    0.25
    /man
    0.25
     wur
    0.24
    Activations Density 0.010%

    No Known Activations