© 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. 22-TRANSCODER-HP
    7. 110965
    Prev
    Next
    INDEX
    Explanations

    Lack of something

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     without
    -0.39
    没æľī
    -0.37
    without
    -0.35
    ä¸įå¿ħ
    -0.33
    Without
    -0.33
    ä¸įåħ·å¤ĩ
    -0.33
     Without
    -0.32
    并没æľī
    -0.32
    ä¸įåĪĨ
    -0.31
    æľªç»ı
    -0.31
    POSITIVE LOGITS
    __[
    0.27
     thumbs
    0.27
    人æµģ
    0.25
    agna
    0.25
    Ctrls
    0.24
    iffin
    0.24
    祢
    0.24
     polar
    0.23
    éĥħ
    0.23
     sez
    0.23
    Activations Density 0.080%

    No Known Activations