© 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. 58639
    Prev
    Next
    INDEX
    Explanations

    increase

    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
     Scot
    -0.27
    isson
    -0.25
    åľ°å¸¦
    -0.25
    cellent
    -0.24
    ä½ķåĨµ
    -0.24
    urge
    -0.23
    ä»ĸ说
    -0.23
    为æĤ¨æıIJä¾Ľ
    -0.23
    tem
    -0.23
    主ç¼ĸ
    -0.23
    POSITIVE LOGITS
    olation
    0.28
    *i
    0.25
     sag
    0.24
     focus
    0.24
    crow
    0.24
    ëŀĮ
    0.23
    /de
    0.23
    ystone
    0.23
    :i
    0.23
     stoi
    0.22
    Activations Density 0.224%

    No Known Activations