© 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. 30963
    Prev
    Next
    INDEX
    Explanations

    $a$, $b$ sequence

    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¿Ļéģĵ
    -0.07
    urs
    -0.06
    第äºĮä½į
    -0.06
    é©°åIJį
    -0.06
    èĩªåĪ¶
    -0.06
    ä¹°çĤ¹
    -0.06
    Traits
    -0.06
    áĥłáĥĺ
    -0.06
    OTS
    -0.06
    irro
    -0.06
    POSITIVE LOGITS
    incerely
    0.07
    ä¸ĢäºĮ
    0.07
    itelist
    0.07
    æŀ
    0.07
    æĻ¶æĻ¶
    0.07
    erland
    0.07
    lardır
    0.07
    檬
    0.07
    lers
    0.07
    就好äºĨ
    0.07
    Activations Density 0.044%

    No Known Activations