© 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. 47639
    Prev
    Next
    INDEX
    Explanations

    previous + noun

    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
    åħ¼æĢ»ç»ıçIJĨ
    -0.07
    å½ĵåīįä½įç½®
    -0.07
    æīĢå±ŀåĪĨç±»
    -0.07
    -await
    -0.07
    ilst
    -0.07
    CurrentUser
    -0.07
    çīį
    -0.07
    &id
    -0.07
    ганÑĤ
    -0.07
    缴
    -0.07
    POSITIVE LOGITS
    代çIJĨ
    0.07
     Lounge
    0.07
    /original
    0.07
    èĵ¬
    0.07
    decision
    0.07
     decision
    0.07
    roma
    0.06
    Decision
    0.06
     Decision
    0.06
    eway
    0.06
    Activations Density 0.005%

    No Known Activations