© 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. 3418
    Prev
    Next
    INDEX
    Explanations

    technical programming terms

    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
     enten
    -0.08
    heb
    -0.08
    —including
    -0.08
     EITHER
    -0.08
     είÏĦε
    -0.07
    kör
    -0.07
    _MULT
    -0.07
    irror
    -0.07
    æĹ¢è¦ģ
    -0.07
    纵
    -0.07
    POSITIVE LOGITS
     etc
    0.08
    ä»Ģä¹ĪçļĦ
    0.08
     maybe
    0.08
    æĪĸåħ¶å®ĥ
    0.07
    çŃīåħ¶ä»ĸ
    0.07
    äºĨåij¢
    0.07
     or
    0.07
    æĪĸèĢħåħ¶ä»ĸ
    0.07
     perhaps
    0.06
     meanwhile
    0.06
    Activations Density 0.016%

    No Known Activations