© 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. 61139
    Prev
    Next
    INDEX
    Explanations

    power, reach, sensitivity, performance

    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
     fiat
    -0.07
    æļĤè¡Į
    -0.07
    éĶ®
    -0.07
    ä»İæĪijåģļèµ·
    -0.07
    æĹłåºı
    -0.06
    acro
    -0.06
    æĹłéĻħ
    -0.06
    ç«ŀ彩
    -0.06
    _INTR
    -0.06
     Gazette
    -0.06
    POSITIVE LOGITS
    æĺŃ
    0.08
    èł¢
    0.07
    æĹ©æĹ©
    0.07
    åĤ¬äºº
    0.07
    çģµæķı度
    0.07
    ä¹ĭæ¯į
    0.07
    ParameterValue
    0.07
    aley
    0.07
    aises
    0.07
    }@
    0.07
    Activations Density 0.005%

    No Known Activations