© 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. 12982
    Prev
    Next
    INDEX
    Explanations

    except or not applicable

    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
    åIJĮ樣
    -0.06
    epar
    -0.06
    åıĪæĺ¯
    -0.06
    _tp
    -0.06
    åIJĮæł·
    -0.06
    íķĺëĭĪ
    -0.06
    usic
    -0.06
    amaan
    -0.06
    å¼Ģ端
    -0.06
    Ìģ
    -0.06
    POSITIVE LOGITS
    except
    0.10
     except
    0.09
    è¾¾åħĭ
    0.09
    注æĦı
    0.08
    Except
    0.08
    æļ
    0.08
    _except
    0.08
    个人æĪĸ
    0.08
     Except
    0.08
     auÃŁer
    0.07
    Activations Density 0.003%

    No Known Activations