© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 23415
    Prev
    Next
    INDEX
    Explanations

    colobison

    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
    urre
    -0.10
    姿
    -0.08
    abaj
    -0.08
    éĢĤå½ĵ
    -0.07
    egov
    -0.07
    妥
    -0.07
     Haupts
    -0.07
    ahl
    -0.07
    byss
    -0.07
    åĬ£
    -0.07
    POSITIVE LOGITS
    è§ĦèĮĥè¦ģæ±Ĥ
    0.06
    æ£ł
    0.06
    che
    0.06
    ä¼Łäºº
    0.06
    ìłľíķľ
    0.06
    ç§ģæľį
    0.06
    æīĭ足
    0.06
    sit
    0.06
     [[]
    0.06
    åģļæ³ķ
    0.06
    Activations Density 0.007%

    No Known Activations