© 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. 15394
    Prev
    Next
    INDEX
    Explanations

    suppressor, transformation, transport, mechanism

    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
    è¿Ļåı«
    -0.09
    OBO
    -0.09
     meist
    -0.08
    lichsten
    -0.08
    !),
    -0.07
    ×Ĵר
    -0.07
    æ²Ľ
    -0.07
    νομ
    -0.07
     atroc
    -0.07
    èħĬ
    -0.07
    POSITIVE LOGITS
     perhaps
    0.14
     somehow
    0.13
    perhaps
    0.13
     possibly
    0.12
     probably
    0.12
    possibly
    0.12
     maybe
    0.11
     Perhaps
    0.11
    æĪĸ许
    0.11
    æĪĸ许æĺ¯
    0.11
    Activations Density 0.754%

    No Known Activations