© 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. 131057
    Prev
    Next
    INDEX
    Explanations

    articles and reports

    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
    /manual
    -0.28
    å®Įåħ¨æ²¡æľī
    -0.27
     onViewCreated
    -0.26
    èİ·å¾ĹæĦŁ
    -0.25
    座ä½į
    -0.25
    干活
    -0.25
    éļıæŶ
    -0.25
    å½¢æĢģ
    -0.24
     blowjob
    -0.24
     propagated
    -0.24
    POSITIVE LOGITS
    quete
    0.34
    krit
    0.26
    ivers
    0.26
     publishers
    0.25
     lif
    0.25
    à¹Ħร
    0.25
     Certified
    0.24
    osta
    0.24
    CORD
    0.24
    enderit
    0.24
    Activations Density 0.014%

    No Known Activations