© 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. 107264
    Prev
    Next
    INDEX
    Explanations

    Code and programming

    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
    uali
    -0.26
    çĶŁæĢķ
    -0.25
     begins
    -0.25
    ä¸ĸ代
    -0.25
    лÑĭ
    -0.24
    sten
    -0.24
    å¹´å¼Ģå§ĭ
    -0.24
    æłĹ
    -0.24
     vitae
    -0.23
    èĥ½æĬĬ
    -0.23
    POSITIVE LOGITS
    afen
    0.27
    creenshot
    0.26
    beh
    0.26
    uced
    0.25
    Contained
    0.25
    æ¯Ķä¾ĭ
    0.25
    模ç³Ĭ
    0.25
     paragraph
    0.24
    éĶĻ
    0.24
    ึ
    0.23
    Activations Density 0.018%

    No Known Activations