© 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. 107289
    Prev
    Next
    INDEX
    Explanations

    quickly/rapidly

    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
    缮åīį
    -0.29
    å°Ĩ继ç»Ń
    -0.28
    çı¾åľ¨
    -0.28
     Continued
    -0.27
    updating
    -0.27
    "Now
    -0.27
    ä¸įä¼ļ
    -0.27
    ä¸įä¼ļåĨį
    -0.27
    çİ°åľ¨
    -0.27
    ’ll
    -0.27
    POSITIVE LOGITS
     became
    0.33
     took
    0.31
     Dou
    0.28
     gave
    0.27
     theor
    0.27
     rez
    0.27
     prepare
    0.26
     went
    0.26
    æıIJé«ĺäºĨ
    0.25
     bef
    0.25
    Activations Density 0.123%

    No Known Activations