© 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. 99256
    Prev
    Next
    INDEX
    Explanations

    technical explanations

    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
    »¿
    -0.31
    intl
    -0.30
    _require
    -0.28
    ¾ç¤º
    -0.28
     requirement
    -0.28
    ä¹Łå¸ĮæľĽ
    -0.27
     propTypes
    -0.27
    -memory
    -0.26
    çĬĴ
    -0.26
    çĽ¼æľĽ
    -0.25
    POSITIVE LOGITS
     brush
    0.29
    trinsic
    0.27
    ç³»
    0.27
    ä¸ĬéĻIJ
    0.26
    iny
    0.26
    被
    0.26
    äºķ
    0.26
    jo
    0.25
    è´Ŀ
    0.25
    解
    0.25
    Activations Density 0.001%

    No Known Activations