© 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. 15794
    Prev
    Next
    INDEX
    Explanations

    substituted/substituent

    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
     Región
    -0.08
     verme
    -0.08
    ifacts
    -0.08
     _:
    -0.07
    ervers
    -0.07
    اعÙĬ
    -0.07
    vania
    -0.07
     ë§IJ
    -0.07
    ustering
    -0.07
    ł
    -0.07
    POSITIVE LOGITS
     al
    0.07
    çµ®
    0.07
    æķ´çIJĨ
    0.07
     incorporating
    0.07
    è¿ŀ带
    0.07
     combining
    0.07
    娥
    0.07
     relationship
    0.07
     linking
    0.06
     simpl
    0.06
    Activations Density 0.009%

    No Known Activations