© 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. 30-TRANSCODER-HP
    7. 97034
    Prev
    Next
    INDEX
    Explanations

    Mixed content

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_30.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.30.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ritable
    -0.28
     Citizens
    -0.28
     Aç
    -0.26
    .Arg
    -0.25
    æ®·
    -0.25
     Stroke
    -0.24
     tiêu
    -0.24
    dia
    -0.24
    _invoke
    -0.24
     Licensed
    -0.24
    POSITIVE LOGITS
    ukes
    0.27
     Petr
    0.26
    ousand
    0.25
    ús
    0.25
    身
    0.24
    pet
    0.24
    sx
    0.24
    occo
    0.24
    etre
    0.24
     pumping
    0.24
    Activations Density 0.882%

    No Known Activations