© 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. 23-TRANSCODER-HP
    7. 25401
    Prev
    Next
    INDEX
    Explanations

    exert

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    igor
    -0.28
     há»Ļi
    -0.27
    storybook
    -0.26
    zzo
    -0.26
     ($.
    -0.25
    ground
    -0.25
    éħIJ
    -0.24
    Pel
    -0.24
    åľ°éĿ¢
    -0.24
    mph
    -0.24
    POSITIVE LOGITS
     powers
    0.31
    ä¹ĭåĬĽ
    0.28
     powerful
    0.28
    æľīæĿĥ
    0.26
     guarding
    0.25
    Rights
    0.25
    uard
    0.25
    åij±
    0.25
     pops
    0.25
    ively
    0.25
    Activations Density 0.011%

    No Known Activations