© 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. 43050
    Prev
    Next
    INDEX
    Explanations

    proposals and advocacy

    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
    aley
    -0.07
    repid
    -0.06
    idden
    -0.06
    ç¼Ń
    -0.06
    è§Ħéģ¿
    -0.06
    aux
    -0.06
    WithError
    -0.06
     expectancy
    -0.06
    deps
    -0.06
    thanks
    -0.06
    POSITIVE LOGITS
     proposed
    0.12
     proposals
    0.12
     proposal
    0.11
    æıIJè®®
    0.10
    æıIJæ¡Ī
    0.10
     Proposed
    0.10
     proposée
    0.10
     advocated
    0.10
     advocates
    0.10
    ä¸»å¼ł
    0.10
    Activations Density 0.562%

    No Known Activations