© 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. 43956
    Prev
    Next
    INDEX
    Explanations

    the

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ourg
    -0.28
    项
    -0.26
    poons
    -0.26
    isses
    -0.25
     ìŀij
    -0.25
     Resolution
    -0.25
    å°ģ
    -0.25
    两边
    -0.24
    eration
    -0.24
     Least
    -0.24
    POSITIVE LOGITS
    /li
    0.29
     lik
    0.29
     image
    0.28
     heter
    0.26
    otto
    0.26
    image
    0.26
    æĬķ注
    0.25
    acre
    0.25
    hole
    0.25
    rious
    0.25
    Activations Density 0.000%

    No Known Activations