© 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. 61244
    Prev
    Next
    INDEX
    Explanations

    descending order

    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
    çļĦä½İ
    -0.09
    ngo
    -0.08
    æ¯Ķè¾ĥä½İ
    -0.08
    inalg
    -0.08
    _finalize
    -0.07
    èĬĤèĬĤ
    -0.07
    ä¹ĭæľ¬
    -0.07
    หลà¸ļ
    -0.07
    æľªæĿ¥åıijå±ķ
    -0.07
    antina
    -0.07
    POSITIVE LOGITS
    descending
    0.07
    æĦıå¿Ĺ
    0.07
    å¿«çļĦ
    0.06
    龸
    0.06
    -down
    0.06
     convers
    0.06
    onda
    0.06
    è©°
    0.06
    enberg
    0.06
    ussion
    0.06
    Activations Density 0.005%

    No Known Activations