© 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. 3585
    Prev
    Next
    INDEX
    Explanations

    modules, algebras, fields

    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
    æŬ
    -0.08
    unya
    -0.07
    æĶ¾è¿ĩ
    -0.07
    ä»»ä½ķä¸Ģç§į
    -0.07
    uny
    -0.07
    çĩ
    -0.07
    reti
    -0.07
    _any
    -0.07
    vine
    -0.07
    让æĪij们çļĦ
    -0.07
    POSITIVE LOGITS
    åį±
    0.08
    /order
    0.07
    æľīåºıçļĦ
    0.07
    çĭ¬ç«ĭæĢ§
    0.07
    鼾
    0.07
    paralle
    0.07
    /orders
    0.06
    ä¹Łæľªå¿ħ
    0.06
    otti
    0.06
     tits
    0.06
    Activations Density 0.005%

    No Known Activations