© 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. 86740
    Prev
    Next
    INDEX
    Explanations

    tools and technology

    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
    iasi
    -0.34
     exc
    -0.28
     elastic
    -0.27
    xious
    -0.26
    пал
    -0.24
    éĿ¢
    -0.24
    ModelState
    -0.24
    ä¹IJ
    -0.24
     gloss
    -0.23
    umi
    -0.23
    POSITIVE LOGITS
    éĢĨè¡Į
    0.27
    riting
    0.27
    å±IJ
    0.26
    çķĻåŃĺ
    0.25
     Poverty
    0.25
     jurisdictions
    0.24
    å½±åĵįåĬĽçļĦ
    0.24
    å°ı鸣
    0.24
    ritten
    0.23
    é³¥
    0.23
    Activations Density 0.003%

    No Known Activations