© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 19100
    Prev
    Next
    INDEX
    Explanations

    normalize

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ä¸ĩæĪ·
    -0.08
    undur
    -0.08
    æ±ĩ
    -0.08
    ascus
    -0.08
    çĶŁäº§ç®¡çIJĨ
    -0.07
    Õ¡Õ°
    -0.07
    olog
    -0.07
    被æįķ
    -0.07
    çģµæ´»æĢ§
    -0.07
    ussen
    -0.07
    POSITIVE LOGITS
    -normal
    0.08
    normalize
    0.08
    Normalize
    0.07
    ipse
    0.07
    normalized
    0.07
    reira
    0.07
     Normalize
    0.07
    æłĩåĩĨåĮĸ
    0.07
    æİ¥è¿ij
    0.07
    å·®ä¸įå¤ļäºĨ
    0.07
    Activations Density 0.004%

    No Known Activations