© 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. 1830
    Prev
    Next
    INDEX
    Explanations

    `_name` or `Payload` or `scope` or `offset` followed by punctuation

    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
    aille
    -0.08
    è¦ģèµ°
    -0.07
    "Just
    -0.07
    áŀ¶áŁĨ
    -0.07
    æĿĥçļĦ
    -0.07
    ë±ħ
    -0.06
    å¾ĹäºĨ
    -0.06
    åįĥ家
    -0.06
    åIJĦåľ°
    -0.06
    é¼ĵåĬ±åĴĮ
    -0.06
    POSITIVE LOGITS
    ,omitempty
    0.07
    æī§è¡ĮæĥħåĨµ
    0.07
    çĤ¹æ»´
    0.07
    initialized
    0.07
    éģ¥
    0.07
    æĸ°æŧ
    0.06
     unchanged
    0.06
    åĨ»
    0.06
    /original
    0.06
    ä¸İåİŁ
    0.06
    Activations Density 0.038%

    No Known Activations