© 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. 62727
    Prev
    Next
    INDEX
    Explanations

    tolerance and adaptation

    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
    į¼
    -0.08
    amente
    -0.07
     handwritten
    -0.07
    дко
    -0.07
    _NATIVE
    -0.06
     timings
    -0.06
    æĨ¾
    -0.06
    aq
    -0.06
    åĢ¼æѤ
    -0.06
    ord
    -0.06
    POSITIVE LOGITS
    éĢĤåºĶäºĨ
    0.10
    éĢĤåºĶ
    0.10
    èĢIJåıĹ
    0.10
     adaptation
    0.09
    累积
    0.09
    éĺĪåĢ¼
    0.08
    åİĮåĢ¦
    0.08
    éº»æľ¨
    0.08
    ä¸Ģ段æŶéĹ´åIJİ
    0.08
    cum
    0.08
    Activations Density 0.120%

    No Known Activations