© 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. 33-TRANSCODER-HP
    7. 54830
    Prev
    Next
    INDEX
    Explanations

    Technical documents/URLs

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_33.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.33.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    Ĭ¶æĢģ
    -0.31
     realised
    -0.27
    ä¹Łæ²¡æľī
    -0.27
    >\↵
    -0.25
    对她
    -0.24
     cancelled
    -0.24
    );\↵
    -0.24
     treated
    -0.24
    --*/↵
    -0.24
     counsel
    -0.24
    POSITIVE LOGITS
    dbc
    0.29
    #:
    0.29
     Establishment
    0.26
     Gest
    0.25
     Rod
    0.25
    è¡į
    0.24
    æĢİä¹Īçľĭ
    0.24
     Ded
    0.24
    oled
    0.24
     Mae
    0.24
    Activations Density 0.015%

    No Known Activations