© 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. 27-TRANSCODER-HP
    7. 7772
    Prev
    Next
    INDEX
    Explanations

    year

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_27.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.27.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    æķ£åıij
    -0.27
    æ°ij
    -0.26
    ame
    -0.24
    /popper
    -0.24
    æĹ¢èĥ½
    -0.24
    è§ī
    -0.24
    æĢ¥éľĢ
    -0.24
    {Name
    -0.23
    è¿ĩå¾Ĺ
    -0.23
    gz
    -0.23
    POSITIVE LOGITS
    LER
    0.28
     dirs
    0.26
    çŀ½
    0.26
     longitudinal
    0.26
    ä½ľèĢħæľ¬äºº
    0.25
     halfway
    0.25
    /pg
    0.25
    dirs
    0.24
    igi
    0.24
    toMatchSnapshot
    0.23
    Activations Density 0.016%

    No Known Activations