© 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. 9656
    Prev
    Next
    INDEX
    Explanations

    There

    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
    æĢĿç´¢
    -0.32
    -interest
    -0.25
    æľīä¸Ģç§į
    -0.25
     way
    -0.24
    ien
    -0.24
    æĸ¹å¼ı
    -0.24
    è¨İ
    -0.24
    (bc
    -0.24
    (QL
    -0.24
    hyth
    -0.24
    POSITIVE LOGITS
    NotFoundError
    0.32
    IRT
    0.30
    åħĦ
    0.29
    zeros
    0.28
    consult
    0.26
    ZR
    0.25
     eighteen
    0.25
     shoulders
    0.24
    afia
    0.24
     individuals
    0.24
    Activations Density 0.010%

    No Known Activations