© 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. 60501
    Prev
    Next
    INDEX
    Explanations

    impairment, biography, properties, synopsis

    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
    头çŃī
    -0.08
    为äºĨä¿Ŀè¯ģ
    -0.08
    å¦Ĥæŀľæĥ³
    -0.07
    гла
    -0.07
    ÅĻe
    -0.07
    wok
    -0.07
    IfNeeded
    -0.07
    ä»ĸæĥ³
    -0.07
    orc
    -0.07
    AYOUT
    -0.07
    POSITIVE LOGITS
     technical
    0.08
    Technical
    0.08
    åij¼åķ¸
    0.08
     factual
    0.08
     Technical
    0.07
    æľ¬èģĮ
    0.07
    åĴĮåŁºæľ¬
    0.07
    è£ħä¸Ĭ
    0.07
    technical
    0.06
     constat
    0.06
    Activations Density 0.083%

    No Known Activations