© 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. 22109
    Prev
    Next
    INDEX
    Explanations

    two or three key/major/primary

    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
    诸å¦Ĥ
    -0.10
    amah
    -0.08
    头åı·
    -0.07
    ]:
    -0.07
    第ä¸ī款
    -0.07
    ':
    -0.07
    èģĶæĴŃ
    -0.07
    åĮħæĭ¬ä½Ĩä¸įéĻIJäºİ
    -0.07
    移åĬ¨çļĦ
    -0.07
    SURE
    -0.07
    POSITIVE LOGITS
    åīįèĢħ
    0.09
    ä¼ĹæīĢåij¨çŁ¥
    0.08
    äºĮèĢħ
    0.07
    为ä¸Ģä½ĵ
    0.07
    èĪ¬
    0.07
    ÙĩÙħا
    0.07
    åIJİèĢħ
    0.06
    áĢŃáĢ¯áĢ·
    0.06
     alike
    0.06
     latter
    0.06
    Activations Density 0.057%

    No Known Activations