© 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. 95062
    Prev
    Next
    INDEX
    Explanations

    Mixed content, possible code snippets

    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
    xac
    -0.29
     Markus
    -0.28
    .firstChild
    -0.27
    æ£Ĵ
    -0.26
     FML
    -0.25
     Giuliani
    -0.25
    åĻ¢
    -0.25
    ongan
    -0.24
    ippi
    -0.24
    structuring
    -0.24
    POSITIVE LOGITS
    ...
    0.33
    âĢ¦
    0.31
     patch
    0.29
     ...
    0.28
    )...
    0.28
    丸
    0.27
    /classes
    0.27
     bá»įn
    0.26
     there
    0.26
     вÑģÑı
    0.26
    Activations Density 0.897%

    No Known Activations