© 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. 26191
    Prev
    Next
    INDEX
    Explanations

    mechanism, factors, characteristics

    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
    ebo
    -0.08
     à¸Ĺีà¹Īà¸Ķีà¸Ĺีà¹Īสุà¸Ķà¹ĥà¸Ļ
    -0.08
    好åķĬ
    -0.08
    eiro
    -0.08
    oose
    -0.08
    abble
    -0.08
    æŶæ¯ı
    -0.08
    ledning
    -0.08
    ä¹Łä¸įä¾ĭå¤ĸ
    -0.08
    )return
    -0.08
    POSITIVE LOGITS
    åıĬåħ¶
    0.10
    åıĬ
    0.09
    åĴĮæĦıä¹ī
    0.09
    ä¸İä½ľçĶ¨
    0.09
    åıĬ对
    0.08
    åĴĮçī¹çĤ¹
    0.08
    åıĬåIJĦ
    0.08
    ä½ķåľ¨
    0.08
    åĴĮä½ľçĶ¨
    0.07
    以åıĬåľ¨
    0.07
    Activations Density 0.018%

    No Known Activations