© 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. 22593
    Prev
    Next
    INDEX
    Explanations

    `implements` programming interfaces

    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
    走强
    -0.08
    elum
    -0.07
    ek
    -0.07
    atures
    -0.07
    å°Ķé¡¿
    -0.07
     Schä
    -0.07
    ehler
    -0.07
    åģļ强
    -0.07
    agua
    -0.06
    ledge
    -0.06
    POSITIVE LOGITS
    æģĴå¿ĥ
    0.08
    常客
    0.07
    åĢºæĿĥåĢºåĬ¡
    0.07
    acus
    0.07
    aimer
    0.07
    好åŃ©åŃIJ
    0.07
    åħ¼
    0.07
    klet
    0.07
    æ®ĺ
    0.07
    å¸ĮæľĽå¯¹å¤§å®¶æľīæīĢ帮åĬ©
    0.07
    Activations Density 0.140%

    No Known Activations