© 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. 19414
    Prev
    Next
    INDEX
    Explanations

    birds and related species

    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
    oulos
    -0.07
    coln
    -0.07
    otime
    -0.07
     ngá»±a
    -0.07
    æ¶ĮåĬ¨
    -0.07
     Bloom
    -0.06
    иÑģÑĤеÑĢ
    -0.06
    çŁ¿
    -0.06
    èłķåĬ¨
    -0.06
    æĥ«
    -0.06
    POSITIVE LOGITS
    鸣类
    0.15
     bird
    0.14
    鸣
    0.14
     пÑĤи
    0.14
    åķĦ
    0.14
    é³¥
    0.14
    bird
    0.14
    ç¾½æ¯Ľ
    0.13
    翱ç¿Ķ
    0.13
    å±ķç¿ħ
    0.13
    Activations Density 0.199%

    No Known Activations