© 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. 20-TRANSCODER-HP
    7. 64580
    Prev
    Next
    INDEX
    Explanations

    Internal combustion engines

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ,but
    -0.28
    %x
    -0.26
    agrams
    -0.26
    æ¯ĵ
    -0.26
     undoubtedly
    -0.25
    Matchers
    -0.25
     probably
    -0.24
     STILL
    -0.24
    æŀ°
    -0.24
    èĢ¿
    -0.24
    POSITIVE LOGITS
    eph
    0.29
    erp
    0.27
     jac
    0.25
    ovsky
    0.25
     dziaÅĤa
    0.25
     Rodrig
    0.25
    éĩĩ
    0.24
    engine
    0.24
    åľ°çIJĥ
    0.24
    èµĦæľ¬å¸Ĥåľº
    0.24
    Activations Density 3.882%

    No Known Activations