© 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. 61754
    Prev
    Next
    INDEX
    Explanations

    foreign language characters and common words

    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
    -cn
    -0.08
    رة
    -0.08
     Objec
    -0.08
    ickerView
    -0.08
    大年
    -0.08
    ervo
    -0.08
    ahir
    -0.08
    ADOW
    -0.07
    ENARIO
    -0.07
    -INF
    -0.07
    POSITIVE LOGITS
    å±Ģåľ°
    0.06
    åĩ
    0.06
    å·¢
    0.06
     Gazz
    0.06
    ׾×Ļ×Ŀ
    0.06
    æĸĩæ¡Ī
    0.06
    ä¸İå½ĵåľ°
    0.06
     tern
    0.06
     Injection
    0.05
     Fisch
    0.05
    Activations Density 0.006%

    No Known Activations