© 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. 33381
    Prev
    Next
    INDEX
    Explanations

    separating authors or items in lists

    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
    ä¸İå·¥ä½ľ
    -0.06
    **
    -0.06
    æ´
    -0.06
    s
    -0.06
     vy
    -0.06
    OURSE
    -0.05
    è´¸çĦ¶
    -0.05
    ми
    -0.05
    æ±Łè·¯
    -0.05
    å½ĵå¹´
    -0.05
    POSITIVE LOGITS
    ÑģÑĤвов
    0.07
    waran
    0.07
    à¸¹à¸Ľ
    0.07
    å°Ķ夫
    0.07
    ÛĮÙħÛĮ
    0.07
    tru
    0.07
    æ²Ļæ²Ļ
    0.07
    baugh
    0.07
    çĶ·ç§ij
    0.07
    å°±ç»ĵæĿŁäºĨ
    0.07
    Activations Density 0.084%

    No Known Activations