© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 12112
    Prev
    Next
    INDEX
    Explanations

    italics usage

    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
    æ´Ľä¼Ĭ
    -0.08
    æĥ³å°½
    -0.07
    ä¼ļå±ķä¸Ńå¿ĥ
    -0.07
    insic
    -0.07
    zzle
    -0.07
    imba
    -0.07
    è¾Ľåĭ¤çļĦ
    -0.07
    arau
    -0.07
    çł¥
    -0.07
     sofist
    -0.07
    POSITIVE LOGITS
    çĶ¨æ³ķ
    0.09
     punctuation
    0.09
    åĪĨéļĶ
    0.07
    äºĭçĶ±
    0.07
     misuse
    0.07
    æŃ£ç¡®ä½¿çĶ¨
    0.07
    éļĶå¼Ģ
    0.07
    Usage
    0.07
    çľģçķ¥
    0.07
    çĶ¨äºİ
    0.07
    Activations Density 0.010%

    No Known Activations