© 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. 17328
    Prev
    Next
    INDEX
    Explanations

    your collection

    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
    essen
    -0.08
    aye
    -0.06
     synth
    -0.06
    Ùĩ
    -0.06
    ä¹Łå°±æĦıåij³çĿĢ
    -0.06
    åľ¨åħĪ
    -0.06
    èĬ¬
    -0.06
    ãĢħ
    -0.06
    ays
    -0.06
    =%
    -0.06
    POSITIVE LOGITS
    urre
    0.09
    -alt
    0.08
    altar
    0.08
    ider
    0.08
    isman
    0.08
    udir
    0.08
    eliti
    0.07
    è§ģå¾Ĺ
    0.07
    alus
    0.07
    agle
    0.07
    Activations Density 0.043%

    No Known Activations