© 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. 2888
    Prev
    Next
    INDEX
    Explanations

    inverse calculation or assignment

    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
    èī³éĺ³
    -0.10
    armo
    -0.07
    onger
    -0.07
    ç³»ç»Łä¸İ
    -0.07
    chn
    -0.07
    åı¥è¯Ŀ说
    -0.07
    ä½łçŁ¥éģĵåIJĹ
    -0.07
    оÑģÑĤо
    -0.07
    aida
    -0.07
     bowiem
    -0.07
    POSITIVE LOGITS
    使ä¹ĭ
    0.08
    éĢĤå½ĵçļĦ
    0.08
     appropriate
    0.08
    appropriate
    0.07
    éĢĤå½ĵ
    0.07
    jut
    0.07
    导
    0.06
    å½ĵæŶçļĦ
    0.06
    icht
    0.06
     factor
    0.06
    Activations Density 0.007%

    No Known Activations