© 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. 42894
    Prev
    Next
    INDEX
    Explanations

    acts or results

    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
    使ä¹ĭ
    -0.08
    粮油
    -0.07
    åľ¨æīĭ
    -0.07
    _UNDER
    -0.07
    uner
    -0.06
    å¦Ĥæĺ¯
    -0.06
    å½ĵåħ¶
    -0.06
    skal
    -0.06
    ellik
    -0.06
    зни
    -0.06
    POSITIVE LOGITS
    å·²ä¹ħçļĦ
    0.08
    ç©·
    0.08
    dings
    0.08
    ä¸Ģå±Ĭ
    0.08
    è¿ŀèĥľ
    0.07
    acent
    0.07
    ä½łè·Ł
    0.07
    梧
    0.07
    teid
    0.07
    asca
    0.07
    Activations Density 0.283%

    No Known Activations