© 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. 17924
    Prev
    Next
    INDEX
    Explanations

    NSW, Directive, Privacy, División

    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
    <|box_end|>
    -0.08
    ESTE
    -0.08
    ERIC
    -0.08
    çĶŁæĢģçݯå¢ĥå±Ģ
    -0.07
    åĽ½åľŁèµĦæºIJå±Ģ
    -0.07
    éĢĢä¼ijå¹´é¾Ħ
    -0.07
    ceg
    -0.07
    /--
    -0.07
    renz
    -0.07
    esters
    -0.07
    POSITIVE LOGITS
    å®ŀæĸ½çļĦ
    0.07
    ä½°
    0.07
    åĽ½æ°ijç»ıæµİ
    0.06
    lr
    0.06
    .signal
    0.06
    å®ŀæĸ½
    0.06
    æĺ¯æĪijåĽ½
    0.06
    ä¸Ńåįİ人æ°ijåħ±åĴĮåĽ½
    0.06
    l
    0.06
    ow
    0.06
    Activations Density 0.004%

    No Known Activations