© 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. 56240
    Prev
    Next
    INDEX
    Explanations

    not sufficient but

    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
    çľĭæĿ¥
    -0.09
    ä»»ä½ķå½¢å¼ıçļĦ
    -0.09
    ÙĪاب
    -0.08
    oa
    -0.08
    ignored
    -0.08
    çľĭä¾Ĩ
    -0.07
    avig
    -0.07
    åģ¥åº·åĴĮ
    -0.07
    èĻ½çĦ¶æ²¡æľī
    -0.07
    ä½Ĩåıªè¦ģ
    -0.07
    POSITIVE LOGITS
     overshadow
    0.07
    ä¸įå¦Ĥ
    0.07
    说好
    0.07
    ensas
    0.06
    éĢĬ
    0.06
    åĦ¿
    0.06
    èĬ±ä¸Ģ
    0.06
    åĿIJä¸ĭæĿ¥
    0.06
    强è°ĥçļĦæĺ¯
    0.06
    ense
    0.06
    Activations Density 0.009%

    No Known Activations