© 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. 107142
    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
    ĵį
    -0.28
    onso
    -0.25
    xAF
    -0.25
    æ»Ĥ
    -0.24
    娣
    -0.24
    åŁĹ
    -0.24
    journal
    -0.24
    ause
    -0.24
    edBy
    -0.24
     OnTrigger
    -0.24
    POSITIVE LOGITS
     alone
    0.39
    ä»Ĭ年以æĿ¥
    0.29
     comparisons
    0.29
    èĩªæľī
    0.28
     Comparison
    0.28
     comparison
    0.28
    ecz
    0.28
    èĩ³ä»Ĭ
    0.28
     compare
    0.27
    èĢĮå·²
    0.27
    Activations Density 0.936%

    No Known Activations