© 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. 97027
    Prev
    Next
    INDEX
    Explanations

    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
    è¡Įç¨ĭ
    -0.26
    ä¸ĵ访
    -0.26
    .SDK
    -0.25
    æķ´é¡¿
    -0.25
    访è°Ī
    -0.25
    ungan
    -0.24
    éĿ¢
    -0.24
     BaseService
    -0.24
    resh
    -0.24
    ago
    -0.24
    POSITIVE LOGITS
    geb
    0.28
    arrant
    0.27
     ABC
    0.26
     morals
    0.25
    enschaft
    0.25
    çļĦ人æĿ¥è¯´
    0.25
     Elli
    0.25
    StateException
    0.25
    ä¹ĭå¿ĥ
    0.25
    ìļĶ
    0.24
    Activations Density 0.000%

    No Known Activations