© 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. 15853
    Prev
    Next
    INDEX
    Explanations

    percent more or less

    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
    enticate
    -0.09
    æŨ
    -0.09
    eness
    -0.08
    lach
    -0.08
    alow
    -0.08
    lisi
    -0.08
    ¬ģ
    -0.08
    :description
    -0.08
     fek
    -0.08
    ëĭĪëĭ¤
    -0.07
    POSITIVE LOGITS
    å·¦åı³çļĦ
    0.12
     (!
    0.09
    以ä¸ĬçļĦ
    0.08
    (!
    0.08
    ä¹ĭå¤ļ
    0.08
    å·¦åı³
    0.07
    æ±Łå±±
    0.07
     (~
    0.07
    ä¹ĭä¸ĢçļĦ
    0.07
     of
    0.06
    Activations Density 0.143%

    No Known Activations