© 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. 45551
    Prev
    Next
    INDEX
    Explanations

    subjective qualities and states

    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
    ãĥ«ãĥķ
    -0.09
    åĴ¬çīĻ
    -0.08
    chemy
    -0.08
    èĢ³çĽ®
    -0.08
    alent
    -0.08
    游åĪĥ
    -0.08
    çľĭçľĭåIJ§
    -0.08
    "..
    -0.07
    åı¸æ³ķé£İéĻ©
    -0.07
    inker
    -0.07
    POSITIVE LOGITS
    aaaa
    0.11
    iiii
    0.09
    åĮħæĭ¬ä½Ĩä¸įéĻIJäºİ
    0.07
    aaaaaaaa
    0.07
    广大
    0.07
    å®ĩå®Ļ
    0.07
    âĦ¢
    0.07
    åħ¨åĽ½äººæ°ij
    0.07
    AAAA
    0.07
    广大çļĦ
    0.07
    Activations Density 2.223%

    No Known Activations