© 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. 23798
    Prev
    Next
    INDEX
    Explanations

    wrongdoing or illegal acts

    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
    BuilderFactory
    -0.08
    æ¨ĭ
    -0.08
    è¿Ļç§įæĦŁè§ī
    -0.07
    agement
    -0.07
    èī
    -0.07
    车ç¨ĭ
    -0.07
    ä¸ĭæĭī
    -0.07
    _ATTACHMENT
    -0.07
    åĭĿ
    -0.07
    å®ŁæĦŁ
    -0.07
    POSITIVE LOGITS
    è¡Į为
    0.16
    è¡ĮçĤº
    0.15
     behavior
    0.14
    è¡Į为çļĦ
    0.14
    çļĦè¡Į为
    0.13
     behaviour
    0.13
     behaviors
    0.13
    è¡Į为åĴĮ
    0.13
    çŃīè¡Į为
    0.12
    è¿Ļç§įè¡Į为
    0.12
    Activations Density 0.326%

    No Known Activations