© 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. 24-TRANSCODER-HP
    7. 149395
    Prev
    Next
    INDEX
    Explanations

    coding and foreign languages

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     inters
    -0.25
    lse
    -0.25
    .epoch
    -0.25
     MLA
    -0.25
    roma
    -0.24
    newline
    -0.24
    lik
    -0.23
    inia
    -0.23
    ฤ
    -0.23
     Browns
    -0.23
    POSITIVE LOGITS
    她们
    0.28
    zag
    0.27
    heard
    0.27
     Stretch
    0.26
    o
    0.26
    -road
    0.26
    imin
    0.25
    oot
    0.25
    ','',
    0.24
    oop
    0.24
    Activations Density 0.071%

    No Known Activations