© 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. 37959
    Prev
    Next
    INDEX
    Explanations

    access and accessibility

    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
    æĹłåĬĽ
    -0.07
     divisive
    -0.07
    æĺ¯çĶ±äºİ
    -0.07
    æݧåĪ¶æĬĢæľ¯
    -0.06
    æĮģæľīçļĦ
    -0.06
     intolerance
    -0.06
    æļĤè¡Įè§Ħå®ļ
    -0.06
     Stability
    -0.06
    ä¼´éļıçĿĢ
    -0.06
    ihkan
    -0.06
    POSITIVE LOGITS
    æݥ触
    0.12
     доÑģÑĤÑĥпа
    0.11
     access
    0.11
    缴æİ¥æݥ触
    0.11
     contact
    0.11
    æݥ触åĪ°
    0.10
    æݥ觸
    0.10
    à¹Ģà¸Ĥà¹īาà¸ĸึà¸ĩ
    0.10
     accessibility
    0.10
    æݥ触çļĦ
    0.09
    Activations Density 0.161%

    No Known Activations