© 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. 41462
    Prev
    Next
    INDEX
    Explanations

    academic/technical writing

    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
    erce
    -0.28
    umatic
    -0.26
    âĩIJ
    -0.26
    italic
    -0.26
    ITA
    -0.25
    roadcast
    -0.25
     mac
    -0.25
    æĭ¿æĿ¥
    -0.25
    astes
    -0.25
    óg
    -0.24
    POSITIVE LOGITS
    åįī
    0.28
    æĬĬè¿ĻäºĽ
    0.26
    ians
    0.25
    in
    0.24
    å´Ķ
    0.24
    ç³»ç»ŁçļĦ
    0.24
    anos
    0.23
    .in
    0.23
    éĤ£æł·
    0.23
    æij¸
    0.23
    Activations Density 1.992%

    No Known Activations