© 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. 33-TRANSCODER-HP
    7. 54665
    Prev
    Next
    INDEX
    Explanations

    computer programs and internet

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    elves
    -0.28
     debugger
    -0.27
    udson
    -0.27
    AxisAlignment
    -0.26
    _runtime
    -0.25
    .ca
    -0.24
    atically
    -0.24
    CLUDED
    -0.24
    .mit
    -0.23
    ä½
    -0.23
    POSITIVE LOGITS
    åĬ¨æľº
    0.36
     Mot
    0.36
    Mot
    0.35
    mot
    0.33
     MOT
    0.32
     motivated
    0.31
     Mobile
    0.31
     motiv
    0.31
     mot
    0.30
    .mobile
    0.30
    Activations Density 0.043%

    No Known Activations