© 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. 22031
    Prev
    Next
    INDEX
    Explanations

    talking

    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
    Negative Logits
     Tribe
    -0.26
     ivory
    -0.25
    æĪIJåijĺ
    -0.24
    .tie
    -0.24
    èIJĭ
    -0.24
    rosse
    -0.24
     Wich
    -0.24
    berger
    -0.24
    -slide
    -0.24
     Ivory
    -0.23
    POSITIVE LOGITS
    æ·±åħ¥å¼Ģå±ķ
    0.26
    erving
    0.25
    usher
    0.25
    ",__
    0.25
    yme
    0.24
    amientos
    0.24
    akers
    0.24
    çĽĽå¤§
    0.23
    éħįæĸ¹
    0.23
     hormone
    0.23
    Activations Density 0.002%

    No Known Activations