© 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. 51722
    Prev
    Next
    INDEX
    Explanations

    asking for confirmation or opinion

    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
    vus
    -0.07
    好人
    -0.07
    ¹
    -0.07
     Souls
    -0.07
    iek
    -0.07
    çĶĺéľ²
    -0.07
    Ľ
    -0.06
    hee
    -0.06
     STUDI
    -0.06
    usak
    -0.06
    POSITIVE LOGITS
    ÚĨار
    0.07
    vier
    0.07
    BASH
    0.07
    çļĦå¾®ç¬ij
    0.07
    強調
    0.07
     Dai
    0.07
     Recap
    0.06
    æĭĻ
    0.06
    åħģ
    0.06
    认è¯ĨäºĨ
    0.06
    Activations Density 0.138%

    No Known Activations