© 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. 50310
    Prev
    Next
    INDEX
    Explanations

    interior point

    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
    æĬĬæĪij们
    -0.06
    è·¨
    -0.06
    teen
    -0.06
    ä¸Ĭå±±
    -0.06
    ç³»
    -0.06
    å±±ä¸ĭ
    -0.06
    书记
    -0.06
     gespi
    -0.06
    ä¸¤åľº
    -0.06
    _finalize
    -0.06
    POSITIVE LOGITS
    OfClass
    0.08
    çķħéĢļ
    0.08
    èĨı
    0.07
    ëģĦ
    0.07
    åįłæľīçİĩ
    0.07
    Granted
    0.07
    abox
    0.07
    ç¬ĭ
    0.07
    oppable
    0.07
    olated
    0.07
    Activations Density 0.003%

    No Known Activations