© 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. 24-TRANSCODER-HP
    7. 149477
    Prev
    Next
    INDEX
    Explanations

    News snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Fetish
    -0.28
    è¡Ľ
    -0.27
    éħ£
    -0.25
     fetish
    -0.24
    éĽħ
    -0.24
     POINT
    -0.24
    atego
    -0.24
     ÐIJвÑĤоÑĢ
    -0.24
    寸
    -0.24
    \Context
    -0.23
    POSITIVE LOGITS
    ordes
    0.32
    æĶ¯éħį
    0.29
    ä¸ľè¥¿
    0.29
    nameof
    0.28
     dictate
    0.28
    Chart
    0.26
    -chart
    0.26
     Chart
    0.26
    Dict
    0.26
    .dict
    0.25
    Activations Density 0.159%

    No Known Activations