© 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. 47811
    Prev
    Next
    INDEX
    Explanations

    foregoing downlink interference

    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
    踵
    -0.09
    amble
    -0.08
     اÙĦتØŃت
    -0.08
    -faced
    -0.07
    erness
    -0.07
    ibil
    -0.07
    orsi
    -0.07
     lon
    -0.07
    ols
    -0.07
    CommandEvent
    -0.07
    POSITIVE LOGITS
    çľĭä¸ĭ
    0.06
    ocos
    0.06
    ående
    0.06
    мова
    0.06
    æĹħåºĹ
    0.06
    失败çļĦ
    0.06
    zeug
    0.06
    è°ģæĺ¯
    0.06
    Anal
    0.06
    亦çĦ¶
    0.06
    Activations Density 0.002%

    No Known Activations