© 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. 17825
    Prev
    Next
    INDEX
    Explanations

    source URLs

    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
    ÑģÑı
    -0.13
    psilon
    -0.11
    poÅĽred
    -0.10
    quine
    -0.10
    odle
    -0.09
    stroy
    -0.09
    egur
    -0.09
    lessly
    -0.09
    SSION
    -0.09
    enticate
    -0.09
    POSITIVE LOGITS
    i
    0.13
    en
    0.13
    ر
    0.11
    iya
    0.10
    zelfde
    0.10
    iab
    0.10
    ãĤĬ
    0.09
    u
    0.09
    ar
    0.09
    an
    0.09
    Activations Density 0.061%

    No Known Activations