© 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. 56165
    Prev
    Next
    INDEX
    Explanations

    dislocation or subluxation

    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
    alak
    -0.08
    опо
    -0.08
     Porr
    -0.08
    Stretch
    -0.08
    ovens
    -0.08
     cale
    -0.08
    yms
    -0.07
    [âĢ¦
    -0.07
     konflik
    -0.07
     zd
    -0.07
    POSITIVE LOGITS
    ãĤĴèµ·ãģĵ
    0.07
     hinges
    0.07
    轻微çļĦ
    0.07
    æŶåĪ»ä¿ĿæĮģ
    0.06
    Rated
    0.06
    etr
    0.06
     Carr
    0.06
     slightest
    0.06
    åĢ¾åIJij
    0.06
    etri
    0.06
    Activations Density 0.007%

    No Known Activations