© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 37571
    Prev
    Next
    INDEX
    Explanations

    replacement rules

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    åį¡è·¯
    -0.08
    ç±³åħ¶æŀĹ
    -0.08
    æĢ»æ¯Ķ
    -0.08
    ä¸įå¹²
    -0.07
    йм
    -0.07
    aptic
    -0.07
     subplot
    -0.07
    è¿ĻäºĽæķ°æį®
    -0.07
     renov
    -0.07
    viron
    -0.07
    POSITIVE LOGITS
     axiom
    0.08
    æĻ®éģį
    0.08
    orem
    0.08
     foundational
    0.07
    equality
    0.07
     schemas
    0.07
     weakening
    0.07
    çIJ
    0.07
    åĴĮåŁºæľ¬
    0.07
    awn
    0.07
    Activations Density 0.003%

    No Known Activations