© 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. 20-TRANSCODER-HP
    7. 142469
    Prev
    Next
    INDEX
    Explanations

    Positive adjectives

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĩłä¹İ
    -0.36
    å¹¾ä¹İ
    -0.34
    åĩłä¹İæĺ¯
    -0.33
    足足
    -0.30
     infinitely
    -0.29
    _multiplier
    -0.29
     almost
    -0.28
    egin
    -0.28
    åĩłä¹İæīĢæľī
    -0.27
     incredibly
    -0.27
    POSITIVE LOGITS
    éľĢè¦ģ注æĦı
    0.29
     div
    0.28
    ature
    0.28
    çļĦè¯Ŀ
    0.27
    erville
    0.25
    åĩºèµĦ
    0.25
    essaging
    0.24
    ercise
    0.24
     otherwise
    0.24
     targeting
    0.23
    Activations Density 64.666%

    No Known Activations