© 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. 94925
    Prev
    Next
    INDEX
    Explanations

    computer code

    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
    天çĦ¶
    -0.27
    .intellij
    -0.27
     below
    -0.27
    Below
    -0.26
     getModel
    -0.26
    empt
    -0.26
    åĬ¾
    -0.26
    emit
    -0.26
    aste
    -0.26
    cing
    -0.25
    POSITIVE LOGITS
    иÑĤелÑĮ
    0.35
    奥æĸ¯åį¡
    0.28
    _life
    0.27
    prd
    0.27
    -life
    0.27
    иÑĤелÑĮн
    0.26
    seys
    0.25
    __("
    0.24
     life
    0.24
    (pool
    0.24
    Activations Density 0.104%

    No Known Activations