© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 62665
    Prev
    Next
    INDEX
    Explanations

    revised, overcame, missed, mobilized

    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
    表达对
    -0.08
    plx
    -0.08
    ãģ£ãģ¦ãĤĤãĤīãģĨ
    -0.08
    åĵªä¸Ģ个
    -0.08
    ÑĤÑĥÑģ
    -0.08
    æĽ´é«ĺçļĦè¦ģæ±Ĥ
    -0.08
    è§Ħå®ļçļĦåħ¶ä»ĸ
    -0.08
    æŁIJä¸Ģ天
    -0.08
    criptor
    -0.07
    罪éŃģ
    -0.07
    POSITIVE LOGITS
    çļĦæĺ¯
    0.17
    äºĨ
    0.15
    ed
    0.14
    çĿĢ
    0.14
    äºĨ对
    0.11
    äºĨ许å¤ļ
    0.11
    äºĨ两
    0.11
    äºĨå¾Īå¤ļ
    0.11
    äºĨä¸Ģ
    0.11
    äºĨä¸Ģ个
    0.11
    Activations Density 0.006%

    No Known Activations