© 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. 28397
    Prev
    Next
    INDEX
    Explanations

    fictional or hypothetical concepts

    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
    dana
    -0.08
    æĦıæĥ³ä¸įåĪ°çļĦ
    -0.08
     verr
    -0.07
     باÙĦض
    -0.07
    åĩºä¹İ
    -0.07
    缴æİ¥æĪĸ
    -0.07
    è¯ķçĤ¹å·¥ä½ľ
    -0.07
    terer
    -0.07
     Lieu
    -0.07
    dere
    -0.07
    POSITIVE LOGITS
    ä¸İçİ°å®ŀ
    0.10
    èĻļæŀĦ
    0.10
    ä¸İå®ŀéĻħ
    0.09
     fict
    0.09
    èĻļæĭŁ
    0.09
    å®Įç¾İ
    0.09
     hypoth
    0.09
     imaginary
    0.08
     fictional
    0.08
    åģĩ
    0.08
    Activations Density 0.158%

    No Known Activations