© 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. 149433
    Prev
    Next
    INDEX
    Explanations

    code comments

    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
     pinpoint
    -0.28
    å¶Ĥ
    -0.27
     wherever
    -0.26
    .esp
    -0.26
    æľįåĬ¡ä¸Ńå¿ĥ
    -0.26
     UB
    -0.26
    ysts
    -0.26
    éĵ
    -0.25
     sav
    -0.25
    ä¸ĢçĤ¹
    -0.25
    POSITIVE LOGITS
    .getPrice
    0.28
    èIJ¥åħ»
    0.27
    çļĦä»·æł¼
    0.27
    :inline
    0.25
    çļĦä»»åĬ¡
    0.25
    å¹´çĶ±
    0.25
    ressive
    0.24
     YT
    0.24
    çĽIJ
    0.24
     Nile
    0.23
    Activations Density 0.136%

    No Known Activations