© 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. 12-TRANSCODER-HP
    7. 24006
    Prev
    Next
    INDEX
    Explanations

    technical/legal documents

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     feasibility
    -0.25
     ironic
    -0.24
    Fe
    -0.24
     alcoholic
    -0.24
    éĻįèIJ½
    -0.24
     iron
    -0.24
    åĪĿå¿ĥ
    -0.24
     nameof
    -0.24
    compact
    -0.23
     tolerant
    -0.23
    POSITIVE LOGITS
     Cos
    0.31
     ÄIJá»Ļ
    0.28
    imeo
    0.27
    addir
    0.27
    ahead
    0.26
    -count
    0.26
    Cos
    0.25
     getCount
    0.25
     Count
    0.24
    Ahead
    0.24
    Activations Density 0.001%

    No Known Activations