© 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. 25-TRANSCODER-HP
    7. 109331
    Prev
    Next
    INDEX
    Explanations

    detects code or filepaths

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    National
    -0.35
     Nations
    -0.34
     National
    -0.32
     н
    -0.30
     Nero
    -0.30
    _nat
    -0.30
    anine
    -0.29
    Noise
    -0.29
    éĩij
    -0.29
     Nacional
    -0.29
    POSITIVE LOGITS
    weather
    0.26
     balk
    0.25
     khá»ķ
    0.25
     Belgian
    0.24
     brav
    0.24
    ulum
    0.24
     Bellev
    0.24
    ä¹īåĬ¡æķĻèĤ²
    0.24
    ä¹IJåĽŃ
    0.24
    .mul
    0.24
    Activations Density 1.288%

    No Known Activations