© 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. 22380
    Prev
    Next
    INDEX
    Explanations

    a definition or term

    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
    人大
    -0.07
    åı¯èĥ½ä¼ļæľī
    -0.07
    两æŃ¥
    -0.07
    jord
    -0.07
    è¿Ļä¹Īåģļ
    -0.07
    äºİæĺ¯æĪij
    -0.07
    já
    -0.06
    ä¼ļæľīå¾Īå¤ļ
    -0.06
     Bew
    -0.06
     opr
    -0.06
    POSITIVE LOGITS
    ÙĪÙĩ
    0.08
    åıĪ称
    0.07
    è´Łè´£å¯¹
    0.07
    oes
    0.07
    drv
    0.07
    çĶ¨æĿ¥
    0.07
    çŃł
    0.07
    sieme
    0.07
    oping
    0.06
    è¿Ļæĺ¯ä¸Ģ
    0.06
    Activations Density 0.032%

    No Known Activations