© 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. 129119
    Prev
    Next
    INDEX
    Explanations

    References and numbers

    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
    olla
    -0.26
    ä¸įæĪIJ
    -0.26
    å¢ĥ
    -0.25
     circ
    -0.25
     Hom
    -0.24
    ChangedEventArgs
    -0.24
    åĴĮ个人
    -0.24
    enga
    -0.23
    ipt
    -0.23
     hom
    -0.23
    POSITIVE LOGITS
    ä¸Ģæĸ¹éĿ¢
    0.26
    redux
    0.25
    é¥
    0.24
    å¼ĢçĿĢ
    0.24
    ARK
    0.24
    ä¸Ģæĺ¯
    0.24
    ussion
    0.24
    CED
    0.24
    irut
    0.23
    åĩıéĢŁ
    0.23
    Activations Density 0.008%

    No Known Activations