© 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. 130913
    Prev
    Next
    INDEX
    Explanations

    total

    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
    æ¯ıèĤ¡
    -0.27
    Features
    -0.26
    fusc
    -0.25
    features
    -0.25
    éļį
    -0.25
    دÙĪ
    -0.24
    èĥ½åĬĽåĴĮ
    -0.24
    _virtual
    -0.24
    dbg
    -0.24
     ell
    -0.24
    POSITIVE LOGITS
    æ´»
    0.29
    IRM
    0.29
     total
    0.28
    æĢ»
    0.27
    total
    0.27
    thur
    0.26
     steward
    0.26
     zob
    0.26
    éħįåIJĪ
    0.26
     hourly
    0.26
    Activations Density 0.008%

    No Known Activations