© 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. 15076
    Prev
    Next
    INDEX
    Explanations

    "AS IS"

    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
    <tool_response>
    -0.08
    èī²åĪĹ
    -0.08
    isi
    -0.08
    }else
    -0.08
     ÑĢаÑģÑĤÑı
    -0.07
    ä¸Ģ度
    -0.07
    好äºĭ
    -0.07
    äºĶèĬ±
    -0.07
    #elif
    -0.07
    åµĮ
    -0.07
    POSITIVE LOGITS
    utage
    0.08
    æĻļå®ī
    0.07
    é£İéĻ©èĩªæĭħ
    0.07
    OW
    0.06
    chas
    0.06
    åħįè´£
    0.06
    è¿ŀ带
    0.06
    xing
    0.06
     skeletons
    0.06
    Instrument
    0.06
    Activations Density 0.589%

    No Known Activations