© 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. 48222
    Prev
    Next
    INDEX
    Explanations

    Maxim, Hier, Who, Visual, Brid

    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
    æĮĽ
    -0.07
    è«
    -0.07
    /swagger
    -0.07
    </think>
    -0.06
     whopping
    -0.06
    秫
    -0.06
    allax
    -0.06
     somehow
    -0.06
    appable
    -0.06
    åİŁä½ĵ
    -0.06
    POSITIVE LOGITS
    第äºĮç§į
    0.09
    ä¹Łæĺ¯æľĢ
    0.08
    вÑĤоÑĢÑĭÑħ
    0.08
    第äºĮéĺ¶æ®µ
    0.08
    sait
    0.07
    ).-
    0.07
    è¿ĶåĽŀ顶éĥ¨
    0.07
    åħ¶æ¬¡
    0.07
    اتÙĩ
    0.07
    æľĢæľĢ
    0.07
    Activations Density 0.013%

    No Known Activations