© 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. 64210
    Prev
    Next
    INDEX
    Explanations

    newsavedmaps, atinformation, opticss, CSSlider, NUITextInputTraitsRenderer, VCFloatingButtonAction, OBIPHONE

    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
    åĴĮ
    -0.07
     ones
    -0.07
    çļĦ
    -0.07
    s
    -0.06
    ä¸į
    -0.06
    åĬłæĭ¿å¤§
    -0.06
    æIJ
    -0.06
    è¦ģ
    -0.06
    被
    -0.06
    对
    -0.06
    POSITIVE LOGITS
    ingen
    0.10
    ings
    0.10
    uit
    0.09
    iem
    0.09
    ang
    0.09
    imos
    0.09
    ç®Ĺä»Ģä¹Ī
    0.09
    unya
    0.09
    纨
    0.09
    iven
    0.08
    Activations Density 0.520%

    No Known Activations