© 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. 21813
    Prev
    Next
    INDEX
    Explanations

    CD, MacBook, EX, div

    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
    iana
    -0.08
    bars
    -0.07
    мп
    -0.07
    ãĤ¹ãĤŃ
    -0.07
    weit
    -0.07
    ssc
    -0.07
    Õ¡Õ°
    -0.07
     antid
    -0.07
    RP
    -0.06
    иÑģк
    -0.06
    POSITIVE LOGITS
    Ń
    0.07
    æĬ½æŁ¥æ£ĢæŁ¥
    0.07
    /octet
    0.07
    天å®ī
    0.07
    æĢ»æķ°çļĦ
    0.07
    请ä¸İæĪij们èģĶç³»
    0.07
    dad
    0.07
    anches
    0.07
    ä¸Ń空
    0.07
    quier
    0.06
    Activations Density 0.002%

    No Known Activations