© 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. 96791
    Prev
    Next
    INDEX
    Explanations

    User interface interaction

    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
    Not in Any Lists

    No Comments

    Negative Logits
    groupName
    -0.30
    -mask
    -0.27
    alist
    -0.25
    riot
    -0.25
     Depot
    -0.24
    brero
    -0.24
    uitar
    -0.23
     FINAL
    -0.23
     batchSize
    -0.23
    _Final
    -0.23
    POSITIVE LOGITS
    è§ģ
    0.30
     seeing
    0.29
    èįī
    0.29
    æķĻ
    0.29
     See
    0.29
     sees
    0.28
    æıIJä¾ĽäºĨ
    0.28
    å®¡æł¸
    0.28
    è¦ĭ
    0.28
     providing
    0.28
    Activations Density 0.908%

    No Known Activations