© 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. 22308
    Prev
    Next
    INDEX
    Explanations

    Moscow

    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
    æ¸ħæ¥ļçļĦ
    -0.07
    ate
    -0.07
    åĵģçļĦ
    -0.07
    ä¸įå¾Ĺ以任ä½ķ
    -0.07
    èį·
    -0.07
    inv
    -0.06
    å½¼æѤçļĦ
    -0.06
    é«ĺæ¡¥
    -0.06
    æ·±åľ³å¸Ĥç¦ıçĶ°åĮº
    -0.06
    Fir
    -0.06
    POSITIVE LOGITS
    illez
    0.07
    ãĢįãĢĮ
    0.07
    åīįèĢħ
    0.07
    راØŃ
    0.07
    cko
    0.07
    .paths
    0.07
    })(
    0.06
    ALAR
    0.06
    ?>>
    0.06
    ehu
    0.06
    Activations Density 0.074%

    No Known Activations