© 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. 51046
    Prev
    Next
    INDEX
    Explanations

    P <, p <

    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
    ungsweise
    -0.08
    ecure
    -0.07
    ÙİاÙĨ
    -0.07
    лма
    -0.07
    ÙĪغ
    -0.07
    á»ijm
    -0.07
    æľĪèĩ³ä»Ĭ
    -0.07
    âĢ¤
    -0.07
    Js
    -0.07
    cret
    -0.07
    POSITIVE LOGITS
    ек
    0.06
     amongst
    0.06
     Wil
    0.06
    è°
    0.06
    ä¸į缸
    0.06
     learnt
    0.06
    umlu
    0.06
     Bon
    0.06
    ç»Łè®¡åѦ
    0.06
    anos
    0.06
    Activations Density 0.035%

    No Known Activations