© 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. 88708
    Prev
    Next
    INDEX
    Explanations

    too

    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
    Not in Any Lists

    No Comments

    Negative Logits
    KeyType
    -0.26
     Sugar
    -0.26
    å¢Ļä¸Ĭ
    -0.26
    ннÑĭе
    -0.25
    arians
    -0.25
    etes
    -0.24
    ä½łä¹Ł
    -0.24
     Rac
    -0.24
     cot
    -0.24
    CES
    -0.24
    POSITIVE LOGITS
    erville
    0.28
    éĶĻ
    0.25
    æĶ¯æŁ±
    0.25
    éĻIJ
    0.25
     trừ
    0.24
    款
    0.24
    讳
    0.24
    á»Ļng
    0.24
    prt
    0.24
    ients
    0.23
    Activations Density 0.051%

    No Known Activations