© 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. 106930
    Prev
    Next
    INDEX
    Explanations

    in

    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
    bar
    -0.36
     bar
    -0.32
    bars
    -0.30
    store
    -0.29
    æ£Ĵ
    -0.28
    ne
    -0.27
    isha
    -0.27
    ieri
    -0.26
    ·æĸ°
    -0.26
    èŀºæĹĭ
    -0.26
    POSITIVE LOGITS
     GENERIC
    0.30
     Wear
    0.27
     december
    0.26
    ToEnd
    0.25
     suce
    0.25
    _pm
    0.24
    æľįåĬ¡ä½ĵç³»
    0.24
    æķŀå¼Ģ
    0.24
     ostat
    0.24
    iterr
    0.24
    Activations Density 0.919%

    No Known Activations