© 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. 34370
    Prev
    Next
    INDEX
    Explanations

    memory recall or recognition

    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
    ansk
    -0.08
    اÙĦÙĦÙĩ
    -0.07
    æ°¸è¿ľæĺ¯
    -0.07
     Ness
    -0.07
    egen
    -0.07
    زÙĨ
    -0.07
    .sk
    -0.07
    äºijé£ŀ
    -0.07
    æĸ¯åĿ¦
    -0.07
    æ©¡
    -0.07
    POSITIVE LOGITS
     somewhere
    0.12
    Something
    0.09
     Something
    0.09
    æŁIJç§į
    0.09
    something
    0.08
    å¿ĺ
    0.08
    好åĥıæĺ¯
    0.08
     something
    0.08
     quelque
    0.08
     somew
    0.08
    Activations Density 0.411%

    No Known Activations