© 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. 35-TRANSCODER-HP
    7. 38858
    Prev
    Next
    INDEX
    Explanations

    scientific research

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_35.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.35.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    æł¸
    -0.79
     nuclear
    -0.67
     nucle
    -0.61
     nu
    -0.58
     ν
    -0.57
     nucleus
    -0.57
     Nu
    -0.55
     nuclei
    -0.55
     Nuclear
    -0.54
    ν
    -0.51
    POSITIVE LOGITS
    leys
    0.31
    LEY
    0.28
     Soccer
    0.27
    CERT
    0.27
    ockey
    0.27
    ICE
    0.27
    ule
    0.26
     mãi
    0.26
     Vik
    0.26
    LIK
    0.26
    Activations Density 2.490%

    No Known Activations