© 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. 7840
    Prev
    Next
    INDEX
    Explanations

    issue

    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
    éĢħ
    -0.27
    PageIndex
    -0.26
    laces
    -0.26
    UNCH
    -0.25
    insky
    -0.25
    bst
    -0.24
     intervening
    -0.23
    -material
    -0.23
    IJľ
    -0.23
     Lal
    -0.23
    POSITIVE LOGITS
     of
    0.31
    OfWork
    0.30
    ŀĭ
    0.27
    ofire
    0.26
    é¦ĸ
    0.26
    OfSize
    0.25
     của
    0.25
    ¡
    0.24
    okane
    0.24
     brief
    0.24
    Activations Density 0.016%

    No Known Activations