© 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. 9850
    Prev
    Next
    INDEX
    Explanations

    sign, polarity, complement

    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
     Bretagne
    -0.08
    è¿ĩæĪij
    -0.07
    irtual
    -0.07
    æĹłéĹ»
    -0.07
    åı¯æľĽ
    -0.07
    رÙĬا
    -0.07
     McM
    -0.07
    iggins
    -0.07
    çĤ¹æĴŃ
    -0.07
    bpp
    -0.07
    POSITIVE LOGITS
     polarity
    0.08
    -negative
    0.08
    缸åıįçļĦ
    0.08
     inversion
    0.08
     reversal
    0.07
    è´Ł
    0.07
    è²ł
    0.07
     полÑİ
    0.07
     reversing
    0.07
    mant
    0.07
    Activations Density 0.020%

    No Known Activations