© 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. 32-TRANSCODER-HP
    7. 40915
    Prev
    Next
    INDEX
    Explanations

    Code/technical language

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    .charCodeAt
    -0.27
     toJSON
    -0.27
    Eb
    -0.27
    鹦
    -0.27
    аниÑĨ
    -0.27
    aname
    -0.25
    AVE
    -0.25
     Geb
    -0.24
    IGH
    -0.24
    enate
    -0.24
    POSITIVE LOGITS
     narrow
    0.26
    æ®ĭ
    0.25
     wake
    0.25
    ulos
    0.25
     ost
    0.24
    _sel
    0.24
     Estr
    0.24
    æĬ±æŃī
    0.24
     imp
    0.24
     multic
    0.24
    Activations Density 0.010%

    No Known Activations