© 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. 109403
    Prev
    Next
    INDEX
    Explanations

    Scientific/technical publications

    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
    HING
    -0.32
    ât
    -0.27
    �t
    -0.27
    atego
    -0.26
    ’e
    -0.26
    -dat
    -0.25
     INA
    -0.25
    ìĩł
    -0.25
    ocaust
    -0.24
    .fore
    -0.24
    POSITIVE LOGITS
    ude
    0.29
    ju
    0.27
    asper
    0.26
    [^
    0.25
     preval
    0.25
     stages
    0.25
    童年
    0.25
    -stage
    0.25
    äºĮæľŁ
    0.24
     quir
    0.24
    Activations Density 0.183%

    No Known Activations