© 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. 25516
    Prev
    Next
    INDEX
    Explanations

    news

    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
     particular
    -0.30
    trag
    -0.29
    izable
    -0.27
    DIV
    -0.26
     persistent
    -0.26
    dur
    -0.26
     dur
    -0.26
     bid
    -0.26
    gam
    -0.26
     ÑģпиÑģ
    -0.25
    POSITIVE LOGITS
    éĺ¶
    0.29
    çĥŃæ°´
    0.28
    Ñģкоп
    0.26
     createStore
    0.25
    è¿Ľä¿®
    0.24
    Ź
    0.24
     qualitÃł
    0.24
    order
    0.24
    顶å±Ĥ
    0.24
     hottest
    0.24
    Activations Density 0.002%

    No Known Activations