© 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. 40108
    Prev
    Next
    INDEX
    Explanations

    `20` followed by numbers

    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
    à¸ģะ
    -0.06
    å¿«ä¹IJåľ°
    -0.06
    纵
    -0.06
    æĪĸåĽł
    -0.06
    orien
    -0.06
    æ»ĭ
    -0.06
    ä¾Ŀå±±
    -0.06
    ä¾Ŀ
    -0.06
    çĿĽ
    -0.06
    Õ¥Õ¶
    -0.06
    POSITIVE LOGITS
     Alv
    0.08
    agno
    0.08
     kiv
    0.07
    ä¸ĩ次
    0.07
    çĽĸä¸ĸ
    0.07
    á»ijng
    0.07
    æĪijè¦ģè¯Ħ论
    0.07
    idou
    0.07
    boards
    0.07
    æĽ´æĸ°æŶéĹ´
    0.07
    Activations Density 0.478%

    No Known Activations