© 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. 25323
    Prev
    Next
    INDEX
    Explanations

    HTML line breaks

    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
    Not in Any Lists

    No Comments

    Negative Logits
    enter
    -0.27
    溶
    -0.26
    ibt
    -0.25
    gd
    -0.25
    ýt
    -0.24
     sol
    -0.24
    ism
    -0.24
    ç¯Ģ
    -0.24
    ruz
    -0.24
     prolong
    -0.23
    POSITIVE LOGITS
     AUTHORS
    0.27
     Georges
    0.26
    çļĦåŁİå¸Ĥ
    0.25
    urg
    0.24
    lasses
    0.24
    urers
    0.24
     conviction
    0.24
    ufficient
    0.23
    æĶ¥
    0.23
    usher
    0.23
    Activations Density 0.229%

    No Known Activations