© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 34788
    Prev
    Next
    INDEX
    Explanations

    definite advantage or unique challenges

    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
     تÙĤرÙĬب
    -0.09
    ortable
    -0.08
    请ä¸ĭè½½
    -0.08
    åħ¬åı¸æĸ°éĹ»
    -0.07
    缸åħ³éĹ®çŃĶ
    -0.07
    thinkable
    -0.07
     Kantor
    -0.07
    ejas
    -0.07
     assolutamente
    -0.07
     undoubtedly
    -0.07
    POSITIVE LOGITS
    æŁIJäºĽ
    0.10
     depending
    0.09
    æŁIJç§į
    0.09
    ä¹Łåı¯èĥ½
    0.09
    depending
    0.09
    æľªå¿ħ
    0.08
     some
    0.08
     alguna
    0.08
    åľ¨æŁIJäºĽ
    0.08
     someday
    0.08
    Activations Density 0.662%

    No Known Activations