© 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. 12-TRANSCODER-HP
    7. 23914
    Prev
    Next
    INDEX
    Explanations

    will

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_12.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.12.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ining
    -0.29
    кÑĢо
    -0.26
    лÑij
    -0.25
    åįķçĭ¬
    -0.24
    asl
    -0.24
    ActionCreators
    -0.24
    inic
    -0.23
    ä¸ĩ亿
    -0.23
     Spir
    -0.23
     typingsSlinky
    -0.23
    POSITIVE LOGITS
     mistress
    0.26
    emas
    0.25
    drag
    0.25
    ç§Ĩ
    0.24
    lox
    0.24
    usta
    0.24
    rex
    0.24
     marketing
    0.24
    /Framework
    0.24
    ux
    0.24
    Activations Density 0.008%

    No Known Activations