© 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. 56948
    Prev
    Next
    INDEX
    Explanations

    teased bangs

    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
     Safe
    -0.07
     Brief
    -0.07
    注æĦıçĤ¹
    -0.07
    顺åĪ©
    -0.06
    chie
    -0.06
     successfully
    -0.06
     safely
    -0.06
     safe
    -0.06
    cheon
    -0.06
    åıªæĺ¯ä¸Ģ
    -0.06
    POSITIVE LOGITS
     often
    0.09
    å¾Ģå¾Ģæĺ¯
    0.09
    注éĩį
    0.09
    ãģ¨ãģ«ãģĭãģı
    0.09
    often
    0.09
    Often
    0.08
    大éĩıçļĦ
    0.08
    çļĦ大éĩı
    0.08
    大éĩı
    0.08
    ãģĹãģ°
    0.08
    Activations Density 0.046%

    No Known Activations