© 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. 26690
    Prev
    Next
    INDEX
    Explanations

    Oisans-Romanche

    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
    å¡Į
    -0.09
    ician
    -0.07
    ä¸ĢæĬ¹
    -0.07
    审
    -0.07
    å°±æĺ¯ä¸Ģç§į
    -0.07
    黯çĦ¶
    -0.07
    anchise
    -0.07
    å·§
    -0.07
     tilt
    -0.07
    akis
    -0.06
    POSITIVE LOGITS
    idu
    0.08
    adu
    0.07
    iable
    0.07
    ÙĪصÙĦ
    0.07
     PROV
    0.06
    产çļĦ
    0.06
    æĸ½æīĵ
    0.06
    leid
    0.06
    ä»ĸè¿ĺæĺ¯
    0.06
    iage
    0.06
    Activations Density 0.009%

    No Known Activations