© 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. 64690
    Prev
    Next
    INDEX
    Explanations

    column index

    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
    yst
    -0.07
    äºĨä¸ĢåĪĩ
    -0.07
    hum
    -0.06
     conform
    -0.06
    åİ¿å§Ķ常å§Ķ
    -0.06
    weiler
    -0.06
    igel
    -0.06
    顺åĪ©åľ°
    -0.06
    orse
    -0.06
    è¾
    -0.06
    POSITIVE LOGITS
    curity
    0.08
    /head
    0.08
    ä½Ĩä¸įéĻIJäºİ
    0.07
    frig
    0.07
    anship
    0.07
    brace
    0.07
    åĴĮæĸ¹æ³ķ
    0.07
    aisen
    0.07
    attr
    0.07
    AndView
    0.07
    Activations Density 0.008%

    No Known Activations