© 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. 107284
    Prev
    Next
    INDEX
    Explanations

    software licenses/copyright notices

    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
    /#{
    -0.27
     Ends
    -0.25
     objective
    -0.25
    ute
    -0.25
    ëļĿ
    -0.25
     spelling
    -0.24
     Objective
    -0.24
    æ°¨éħ¸
    -0.24
    rzÄĻ
    -0.24
     lining
    -0.23
    POSITIVE LOGITS
    å·²ç»ıæľīäºĨ
    0.27
    sus
    0.27
    Automatic
    0.26
    eguard
    0.26
     penn
    0.26
    æľ¬ä¹¦
    0.25
    raid
    0.25
    otos
    0.24
    æĥ¯
    0.24
     preced
    0.24
    Activations Density 0.005%

    No Known Activations