© 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. 11697
    Prev
    Next
    INDEX
    Explanations

    writings or essays

    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
     perpetr
    -0.07
    old
    -0.07
     Ensemble
    -0.07
    olata
    -0.07
    ä»»ä½ķåħ¶ä»ĸ
    -0.07
     комплекÑĤÑĥ
    -0.07
     incumbent
    -0.07
    ollywood
    -0.06
     gigg
    -0.06
    ä¹ĭ家
    -0.06
    POSITIVE LOGITS
     aph
    0.09
     writings
    0.09
    èijĹä½ľ
    0.09
     essays
    0.08
     ÑģвоиÑħ
    0.08
     essay
    0.08
     Ñģвоем
    0.08
    /book
    0.07
     Ñģво
    0.07
    å°½åħ¶
    0.07
    Activations Density 0.281%

    No Known Activations