© 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. 57383
    Prev
    Next
    INDEX
    Explanations

    KitKat updates

    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
    天ä¸ĭ第ä¸Ģ
    -0.08
    æĭĽèģĺç½ij
    -0.08
     mÃły
    -0.07
    Bindable
    -0.07
    áĥĶáĥľ
    -0.07
    cte
    -0.07
    æł¼å±Ģ
    -0.07
    åĽ¤
    -0.07
     resource
    -0.07
    qn
    -0.07
    POSITIVE LOGITS
    è¾ĥ
    0.07
    åĴĮ帮åĬ©
    0.07
    nak
    0.06
    åľ¨å½ĵæŶ
    0.06
    æłı
    0.06
    adge
    0.06
    ultip
    0.06
    ining
    0.06
    ält
    0.06
    idge
    0.06
    Activations Density 2.009%

    No Known Activations