© 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. 57714
    Prev
    Next
    INDEX
    Explanations

    alternatives, your, very, territory, this, Jud, forward, port

    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
    大åıij
    -0.07
    çĤĻ
    -0.07
    velle
    -0.07
    Views
    -0.07
    æĪĸå¤ļ
    -0.07
    åľ¨ä¸ĭéĿ¢
    -0.06
    à¸ģรà¸ĵà¹Į
    -0.06
    æĹ¶å¸¸
    -0.06
    ensem
    -0.06
     Laden
    -0.06
    POSITIVE LOGITS
     اÙĦÙħØ°Ùĥ
    0.09
    å®ŀå¤Ħ
    0.08
    æıIJåĪ°çļĦ
    0.08
     mentioned
    0.08
    mentioned
    0.07
     effectivement
    0.07
     opendir
    0.07
    æĹ¢çĦ¶
    0.07
     Sipil
    0.07
     Dalle
    0.07
    Activations Density 0.010%

    No Known Activations