© 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. 109559
    Prev
    Next
    INDEX
    Explanations

    face

    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
    cribed
    -0.27
     TObject
    -0.26
     zwar
    -0.26
    èµ°å»Ĭ
    -0.24
    igor
    -0.24
     Reload
    -0.23
     sorts
    -0.23
    IEW
    -0.23
    forcing
    -0.23
    iao
    -0.23
    POSITIVE LOGITS
    éŨ
    0.29
    çīĻ
    0.29
    ants
    0.29
    éĸĢ
    0.27
    rine
    0.27
     constant
    0.25
    _constant
    0.25
    ancy
    0.24
    ặt
    0.24
    çĪ±ç¾İ
    0.23
    Activations Density 0.563%

    No Known Activations