© 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. 7632
    Prev
    Next
    INDEX
    Explanations

    Latv, erland, infeld, Donovan, Adrian

    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
    cky
    -0.07
    atti
    -0.07
    ucci
    -0.06
    esimo
    -0.06
    asher
    -0.06
    ollo
    -0.06
    论
    -0.06
    è«ĸ
    -0.06
    chn
    -0.06
    æ¯ĭ
    -0.06
    POSITIVE LOGITS
    :host
    0.09
    agas
    0.08
    æĬķæĶ¾
    0.08
    leet
    0.08
    erland
    0.07
    infeld
    0.07
     Donovan
    0.07
     retarded
    0.07
    תר
    0.07
    马éŀįå±±
    0.07
    Activations Density 0.008%

    No Known Activations