© 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. 10298
    Prev
    Next
    INDEX
    Explanations

    code block context, data structures, variables

    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
    ;)
    -0.09
    plo
    -0.07
     }>
    -0.07
     ];
    -0.07
    ;j
    -0.07
    æĪijåĴĮå¦Īå¦Ī
    -0.06
    ;k
    -0.06
    '%(
    -0.06
    !:
    -0.06
     ï¼Ī
    -0.06
    POSITIVE LOGITS
    ä½Ĩä¸įéĻIJäºİ
    0.09
    ,
    0.08
    ana
    0.07
    èī¾å°Ķ
    0.07
    ä¸įæĺ¯è¯´
    0.07
    ahoma
    0.07
    enser
    0.07
     _)
    0.07
    avana
    0.07
    AAF
    0.07
    Activations Density 0.028%

    No Known Activations