© 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. 20924
    Prev
    Next
    INDEX
    Explanations

    shift in wavelength or frequency

    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
    arkan
    -0.08
    çĸĹ
    -0.07
    åºĶç¨İ
    -0.07
     préfér
    -0.07
     frontier
    -0.07
    ÙĪÙĬÙĦ
    -0.07
    _supply
    -0.07
    supply
    -0.07
    iliki
    -0.07
     supply
    -0.07
    POSITIVE LOGITS
    æĶ¹æŃ£
    0.09
    æķıæĦŁåº¦
    0.09
     alteration
    0.08
     subtle
    0.08
    å¼ķèµ·çļĦ
    0.08
     noticeable
    0.08
    æ¯ıå¹´
    0.08
    æīĢå¼ķèµ·çļĦ
    0.08
     devia
    0.08
     affecting
    0.08
    Activations Density 0.026%

    No Known Activations