© 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. 151432
    Prev
    Next
    INDEX
    Explanations

    Nations/Languages

    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
    Negative Logits
    æĻ¯
    -0.29
    /init
    -0.28
     Holden
    -0.25
    uit
    -0.25
     Hammond
    -0.24
    髯
    -0.24
    EEE
    -0.24
    uin
    -0.24
     Lynch
    -0.24
    imuth
    -0.24
    POSITIVE LOGITS
     sovereignty
    0.31
     Sovere
    0.30
    é¢ĨåľŁ
    0.28
    çĿ¦
    0.27
    (dm
    0.26
    æīĢæľīæĿĥ
    0.26
    adm
    0.25
     dropping
    0.24
    ti
    0.24
     Wash
    0.24
    Activations Density 0.943%

    No Known Activations