© 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. 25-TRANSCODER-HP
    7. 107258
    Prev
    Next
    INDEX
    Explanations

    Source code/unidentified text

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    elles
    -0.29
    -mouth
    -0.27
    ="""
    -0.27
     Cognitive
    -0.26
     Nose
    -0.25
    åĬ¨çĶŁæĪIJ
    -0.25
    -mounted
    -0.24
     McCart
    -0.24
     Helmet
    -0.23
    	cpu
    -0.23
    POSITIVE LOGITS
     prestige
    0.26
    继ç»Ń
    0.26
     dime
    0.25
    æĸĹäºī
    0.25
    å°Ĩ继ç»Ń
    0.24
    è¯ķçĿĢ
    0.24
     Dickinson
    0.24
    ç²¾èĭ±
    0.24
    >>)
    0.23
    æľīæŶ
    0.23
    Activations Density 0.882%

    No Known Activations