© 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. 151112
    Prev
    Next
    INDEX
    Explanations

    up

    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
    éĽĩ
    -0.31
    caffold
    -0.27
    /**↵↵
    -0.25
     Lodge
    -0.25
    ']}'
    -0.25
    ised
    -0.24
     capitals
    -0.24
    èIJ¥
    -0.24
     flakes
    -0.23
    循
    -0.23
    POSITIVE LOGITS
     with
    0.30
     wit
    0.28
    olls
    0.27
     Lust
    0.27
    wit
    0.26
    鸳
    0.26
    oten
    0.25
    inder
    0.25
     operation
    0.25
    bine
    0.25
    Activations Density 0.108%

    No Known Activations