© 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. 32-TRANSCODER-HP
    7. 40806
    Prev
    Next
    INDEX
    Explanations

    prevent

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_32.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.32.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
     def
    -0.28
    èĬĿ
    -0.27
    def
    -0.27
    ãĥĪãĥĥãĥĹ
    -0.26
    ç»ıéªĮåĴĮ
    -0.26
    é¾Ļæ¹ĸ
    -0.26
    tees
    -0.25
    .Foundation
    -0.24
    æ²»
    -0.24
     kob
    -0.24
    POSITIVE LOGITS
    opsis
    0.28
    âį¨
    0.28
    ç³ł
    0.27
    åħ¥åľº
    0.25
    æ²¹èĦĤ
    0.25
    å¨ģå°Ķ
    0.25
    USTER
    0.25
     Sole
    0.25
    ç¨
    0.24
    Issue
    0.24
    Activations Density 0.001%

    No Known Activations