© 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. 39971
    Prev
    Next
    INDEX
    Explanations

    change/changes

    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
    aint
    -0.08
    utow
    -0.07
    earch
    -0.07
    rens
    -0.07
     fil
    -0.07
    лой
    -0.07
    æŀĹç«ĭ
    -0.07
    çĭ¬
    -0.07
    _DIG
    -0.07
    belt
    -0.07
    POSITIVE LOGITS
    åıijçĶŁåľ¨
    0.09
    /change
    0.09
    å¹ħ度
    0.09
    Occurred
    0.08
     ÎĶ
    0.07
     (-
    0.07
     changes
    0.07
    (change
    0.07
     ÎĶη
    0.07
     (+
    0.07
    Activations Density 0.012%

    No Known Activations