© 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. 62573
    Prev
    Next
    INDEX
    Explanations

    high temperatures or creep

    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
    ĻĤ
    -0.08
    æī°ä¹±
    -0.07
    æīĵæİī
    -0.07
    æ³½
    -0.07
    amus
    -0.07
    æľŃ
    -0.07
    éĩİèĽ®
    -0.07
    hé
    -0.07
     brut
    -0.07
    åłĤçļĦ
    -0.07
    POSITIVE LOGITS
    åľ¨é«ĺ温
    0.10
    çļĦé«ĺ温
    0.09
     creep
    0.09
    èłķ
    0.09
    é«ĺ温
    0.08
    çĪ¬
    0.08
    æŶéĹ´éķ¿
    0.08
    itzen
    0.07
    æ¸ĹéĢı
    0.07
    æĶĢ
    0.07
    Activations Density 0.014%

    No Known Activations