© 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. 149240
    Prev
    Next
    INDEX
    Explanations

    snap

    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
    Negative Logits
     principal
    -0.28
    ä¼IJ
    -0.28
    (Graph
    -0.25
     princip
    -0.25
    tera
    -0.24
     few
    -0.24
    Ģ
    -0.24
    ẵ
    -0.23
     har
    -0.23
     sur
    -0.22
    POSITIVE LOGITS
    rance
    0.29
    nings
    0.29
    uckets
    0.27
    é²ľæ´»
    0.26
    å¸Ĥå§Ķ书记
    0.26
     Reception
    0.25
    ousel
    0.25
    çļĦä¼łç»Ł
    0.25
    bcrypt
    0.25
    ç§ijæĬĢ大åѦ
    0.25
    Activations Density 0.116%

    No Known Activations