© 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. 14-TRANSCODER-HP
    7. 41525
    Prev
    Next
    INDEX
    Explanations

    straightforward

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_14.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.14.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     role
    -0.27
     seat
    -0.24
     fires
    -0.23
    大èĥĨ
    -0.23
    éĩįçĤ¹
    -0.23
    benh
    -0.23
     secara
    -0.23
     future
    -0.23
     kone
    -0.23
    uran
    -0.23
    POSITIVE LOGITS
    olk
    0.30
    ICH
    0.28
     OCC
    0.25
    çļĦæĥħ
    0.25
    iw
    0.25
    거리
    0.25
    spb
    0.24
     )->
    0.24
    à¹Ģà¸ģ
    0.24
     tended
    0.23
    Activations Density 1.613%

    No Known Activations