© 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. 32-TRANSCODER-HP
    7. 40909
    Prev
    Next
    INDEX
    Explanations

    critical

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    iard
    -0.26
    è¶Ł
    -0.26
    éĿ¢èī²
    -0.25
     Fav
    -0.25
    ä¸Ģè¶Ł
    -0.24
    åij½åIJį为
    -0.24
    ä¸ĢæľŁ
    -0.24
    Titles
    -0.24
    龸çİĭ
    -0.24
    wahl
    -0.24
    POSITIVE LOGITS
     critical
    0.71
    critical
    0.63
     Critical
    0.60
    Critical
    0.57
    _critical
    0.46
     critically
    0.43
    ritical
    0.42
    åħ³éĶ®
    0.38
     crit
    0.36
     deeper
    0.36
    Activations Density 0.002%

    No Known Activations