© 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. 62009
    Prev
    Next
    INDEX
    Explanations

    proper noun following colon

    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
    该款
    -0.08
    åıijçİ°åľ¨
    -0.08
    Õ®
    -0.07
    aad
    -0.07
    åĩłæ¬¾
    -0.07
    spec
    -0.07
    åľ°çĽ¯çĿĢ
    -0.07
    åıijçĶŁè¿ĩ
    -0.07
     Äijá»ĵn
    -0.07
    ×ķ×ĺ
    -0.07
    POSITIVE LOGITS
    åį°
    0.08
    repid
    0.07
    PRINTF
    0.06
    ä¸įè¨Ģ
    0.06
    lius
    0.06
    liz
    0.06
    ä¿¡æģ¯ä¸Ńå¿ĥ
    0.06
    åºľ
    0.06
     viv
    0.06
    airo
    0.06
    Activations Density 0.009%

    No Known Activations