© 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. 14-TRANSCODER-HP
    7. 41399
    Prev
    Next
    INDEX
    Explanations

    URLs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    欢è¿İæĤ¨
    -0.26
    Subtitle
    -0.25
    主ç¼ĸ
    -0.25
    nal
    -0.25
    ç«łèĬĤ
    -0.25
    大åħ¨
    -0.24
    леж
    -0.23
    缴åįĩæľº
    -0.23
    á»ijn
    -0.23
    _subtitle
    -0.23
    POSITIVE LOGITS
    ariat
    0.30
    #elif
    0.28
    aset
    0.26
    çIJĨäºĭä¼ļ
    0.26
    ä¸į顾
    0.25
     Hag
    0.24
    -pos
    0.24
    æ§Į
    0.24
    @@@@
    0.24
    ».
    0.24
    Activations Density 0.162%

    No Known Activations