© 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. 10701
    Prev
    Next
    INDEX
    Explanations

    searching for paths

    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
    uschen
    -0.08
     unavoidable
    -0.06
    æł¼éĽ·
    -0.06
    olds
    -0.06
    æĭĨè£ħ
    -0.06
    ä¸įåı¯éģ¿åħį
    -0.06
    .newLine
    -0.06
    istring
    -0.06
    enk
    -0.06
    å¿ħ
    -0.06
    POSITIVE LOGITS
    寻æī¾
    0.15
    寻è§ħ
    0.14
    æŁ¥æī¾
    0.13
    å°ĭæī¾
    0.13
     searching
    0.13
     search
    0.13
     поиÑģ
    0.13
    æī¾çļĦ
    0.13
     поиÑģк
    0.12
    æī¾å¯»
    0.12
    Activations Density 0.119%

    No Known Activations