© 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. 98951
    Prev
    Next
    INDEX
    Explanations

    Web content snippets

    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
    *T
    -0.27
    èĢĮåľ¨
    -0.26
    äºĴ
    -0.26
    浪
    -0.25
    Cl
    -0.24
    绣ä¸Ģ
    -0.24
    Confirmation
    -0.24
    亥
    -0.24
     rather
    -0.24
     vs
    -0.23
    POSITIVE LOGITS
    øj
    0.28
    antino
    0.27
     NDEBUG
    0.27
    æĹ¥æĬ¥ç¤¾
    0.26
     Berm
    0.25
     fund
    0.25
    åĽ½åĬ¡
    0.24
    æı©
    0.24
    adows
    0.24
    eming
    0.24
    Activations Density 0.006%

    No Known Activations