© 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. 24432
    Prev
    Next
    INDEX
    Explanations

    being analyzed

    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
    å·²å°Ĩ
    -0.10
    导åĩºæķ°æį®
    -0.09
    å·²ç»ĵæĿŁ
    -0.09
    è¦ģå°Ĩ
    -0.08
    è¦ģæĬĬ
    -0.08
    ÑĪев
    -0.08
    åı¯å°Ĩ
    -0.08
    åħ³éĹŃçªĹåı£
    -0.08
    ooky
    -0.08
    åı¯ä»¥æĬĬ
    -0.08
    POSITIVE LOGITS
    å½ĵä½ľ
    0.09
    åĬłä»¥
    0.08
    çĶ±åİŁåijĬ
    0.08
    æݨåIJij
    0.07
    Ỽm
    0.07
    è§Ĩ为
    0.07
    è¿ĺ被
    0.07
     à¸ĸูà¸ģ
    0.07
    交çĶ±
    0.07
     subjected
    0.07
    Activations Density 0.964%

    No Known Activations