© 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. 22212
    Prev
    Next
    INDEX
    Explanations

    gest

    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
    诰
    -0.27
    Draft
    -0.26
    -face
    -0.26
    ¢åįķ
    -0.25
    enties
    -0.25
    SOR
    -0.24
    ä¾Ŀæ³ķ追究
    -0.24
    afe
    -0.24
     Ves
    -0.24
     Crafts
    -0.24
    POSITIVE LOGITS
     none
    0.28
     ste
    0.27
     vaz
    0.27
    èĤ¡
    0.27
     None
    0.25
    涵
    0.25
    .keyboard
    0.24
    empt
    0.24
    	buttons
    0.24
    è§ļ
    0.24
    Activations Density 0.237%

    No Known Activations