© 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. 25892
    Prev
    Next
    INDEX
    Explanations

    first, second, currency, auxiliary, support, WB

    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
    osit
    -0.08
    å°Ĭ
    -0.07
    form
    -0.06
    é¡·
    -0.06
    aina
    -0.06
    æīĢæľª
    -0.06
     form
    -0.06
     sw
    -0.06
    åıĬæł¼
    -0.06
    rist
    -0.06
    POSITIVE LOGITS
    pere
    0.08
    oogle
    0.08
    ftar
    0.08
     Polis
    0.08
    chief
    0.08
    orgen
    0.08
    ASURE
    0.08
    enciales
    0.08
    ิà¸ģ
    0.08
    APO
    0.07
    Activations Density 0.060%

    No Known Activations