© 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. 22747
    Prev
    Next
    INDEX
    Explanations

    ratio or quantity

    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
    æ®·
    -0.07
     fuzz
    -0.07
    å·ŀæĶ¿åºľ
    -0.07
    ä»»
    -0.07
    kr
    -0.06
    åħ·ä½ĵ
    -0.06
    åħ·ä½ĵåĨħ容
    -0.06
    åħ·ä½ĵæŶéĹ´
    -0.06
     Setter
    -0.06
    åħ·ä½ĵè¦ģæ±Ĥ
    -0.06
    POSITIVE LOGITS
     autant
    0.08
    ë§Įíģ¼
    0.08
    åĮ¹éħį
    0.07
    matched
    0.07
    çİĭæĢĿ
    0.07
     altrett
    0.07
    è·Łåįķ
    0.07
    untos
    0.07
    æĿŀ
    0.07
     matched
    0.07
    Activations Density 0.018%

    No Known Activations