© 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. 95063
    Prev
    Next
    INDEX
    Explanations

    whole

    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
    å¼Ģå¥ĸ
    -0.26
    ìĽĮ
    -0.25
     Jac
    -0.25
     event
    -0.25
    ä¸Ģå¿ĥ
    -0.24
    çĦ¦çĤ¹
    -0.24
    éĽī
    -0.24
    iard
    -0.24
    åĽŀåºĶ
    -0.24
    getRow
    -0.23
    POSITIVE LOGITS
    é£Łçī©
    0.32
    anko
    0.27
    åIJĥçļĦ
    0.26
    auen
    0.26
    å¨ĥ
    0.25
    uggle
    0.25
    alen
    0.24
    身
    0.24
    rz
    0.24
    é£ŁæĿIJ
    0.24
    Activations Density 0.888%

    No Known Activations