© 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. 25001
    Prev
    Next
    INDEX
    Explanations

    legal or policy violations

    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
    ç§ķ
    -0.08
    å¾Ĺ人
    -0.08
    ammel
    -0.08
    NotFoundError
    -0.08
     sekaligus
    -0.08
     everywhere
    -0.07
    çĽIJåĴĮ
    -0.07
    çĶ¸çĶ¸
    -0.07
    bcm
    -0.07
    âĢ¦and
    -0.07
    POSITIVE LOGITS
    æĢ§æĪĸ
    0.18
    å¤įåĪ¶æĪĸ
    0.17
    人æĪĸ
    0.17
    å·¥ä½ľæĪĸ
    0.17
    æĬķèµĦæĪĸ
    0.17
    æĸĩ件æĪĸ
    0.16
    æĪĸèĢħæľī
    0.16
    ê±°ëĤĺ
    0.16
    æĪĸåħ¶
    0.16
    æĪĸåħ¶ä»ĸ
    0.15
    Activations Density 0.156%

    No Known Activations