© 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. 30679
    Prev
    Next
    INDEX
    Explanations

    constant","intercept","equal","require","should"

    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
    usser
    -0.07
     gr
    -0.06
    ä¸ĢåĽ¢
    -0.06
    é¢ĨéĺŁ
    -0.06
    éŀ
    -0.06
    /state
    -0.06
    achine
    -0.06
    anche
    -0.06
    ("\\
    -0.06
    ä¼Ļä¼´åħ³ç³»
    -0.06
    POSITIVE LOGITS
    rint
    0.07
    估计
    0.07
     Intercept
    0.07
     Neues
    0.07
     estimated
    0.07
    çѱ
    0.07
    æĶ¶åĪ°çļĦ
    0.07
    çĨ
    0.07
    å¹´çĶŁ
    0.07
    ä¼°è¨Ī
    0.07
    Activations Density 0.002%

    No Known Activations