© 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. 39490
    Prev
    Next
    INDEX
    Explanations

    saved from disaster or bad luck

    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
    ä¸Ģæ¦Ĥ
    -0.08
    åıªè¦ģæĺ¯
    -0.07
     incor
    -0.07
    strup
    -0.07
    esis
    -0.07
    пÑĤа
    -0.07
    arger
    -0.07
    ä¸įå¦Ĥ
    -0.07
    æ°¸è¿ľæĺ¯
    -0.07
    èĸ°
    -0.06
    POSITIVE LOGITS
    å·®çĤ¹
    0.13
    幸äºı
    0.13
    éĻ©äºĽ
    0.12
    åºĨ幸
    0.12
    幸
    0.12
    çļĦåį±éĻ©
    0.12
    åį±éĻ©
    0.12
     saved
    0.11
    幸好
    0.11
    saved
    0.11
    Activations Density 0.323%

    No Known Activations