© 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. 61781
    Prev
    Next
    INDEX
    Explanations

    case numbers

    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
    è®
    -0.06
    没æľīä¸ĢçĤ¹
    -0.06
    Alternate
    -0.06
    åį§
    -0.06
    ð
    -0.06
     vie
    -0.06
    好ä¸į容æĺĵ
    -0.06
    ä¸įèĪį
    -0.06
    que
    -0.06
    ATCH
    -0.06
    POSITIVE LOGITS
    strup
    0.08
    游åŃIJ
    0.08
    urf
    0.07
    hue
    0.07
    ctal
    0.07
    çĪ¹
    0.07
    æľīå¥ĸ
    0.07
    ược
    0.07
    åı¸
    0.07
    idez
    0.07
    Activations Density 0.070%

    No Known Activations