© 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. 49847
    Prev
    Next
    INDEX
    Explanations

    legislative proposals and bills

    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
    ä¸Ĭå½ĵ
    -0.08
    åĭī
    -0.07
    hots
    -0.07
    /console
    -0.07
    vens
    -0.07
     contracted
    -0.07
    åĬłçĽŁ
    -0.07
    å·²å®Įç»ĵ
    -0.07
    åIJĮçIJĨ
    -0.07
    è²·ãģ£ãģŁ
    -0.07
    POSITIVE LOGITS
     proposed
    0.16
     proposals
    0.16
     proposal
    0.16
     proposing
    0.14
    æıIJè®®
    0.14
     proposta
    0.13
    èįīæ¡Ī
    0.13
     proposes
    0.13
     proposte
    0.13
     Proposed
    0.13
    Activations Density 0.290%

    No Known Activations