© 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. 10759
    Prev
    Next
    INDEX
    Explanations

    links to images or files

    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
    è´§åĪ°
    -0.07
    éªĦåĤ²
    -0.07
     ass
    -0.07
    uala
    -0.06
    esser
    -0.06
    unner
    -0.06
    è¾¾åħĭ
    -0.06
    _SA
    -0.06
    æĿ¥ä¹ĭä¸įæĺĵ
    -0.06
    çļĪ
    -0.06
    POSITIVE LOGITS
    ico
    0.08
    碰碰
    0.08
    istro
    0.08
    æľªæŀľ
    0.07
    ä¸īæĹł
    0.07
    ä¸įæĶ¾å¼ĥ
    0.07
    该éĻ¢
    0.07
    icus
    0.07
    æ¬Ĭ
    0.07
    ä¿¡å¿ĥåĴĮ
    0.07
    Activations Density 0.119%

    No Known Activations