© 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. 12822
    Prev
    Next
    INDEX
    Explanations

    measures and metrics

    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
     pouc
    -0.08
     convinto
    -0.07
    ÏĦÏį
    -0.07
    ç¼ĺæķħ
    -0.07
    IDDLE
    -0.07
    çļĦç¼ĺæķħ
    -0.07
     coinciden
    -0.07
    estero
    -0.07
    ceed
    -0.07
    è§Ħå¾ĭ
    -0.07
    POSITIVE LOGITS
    è¡¡éĩı
    0.17
     measures
    0.16
     metrics
    0.16
    æĮĩæłĩ
    0.15
     measure
    0.14
     indicators
    0.13
    è¯Ħä»·æĮĩæłĩ
    0.13
     Measures
    0.13
     measuring
    0.13
     Metrics
    0.13
    Activations Density 0.209%

    No Known Activations