© 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. 55378
    Prev
    Next
    INDEX
    Explanations

    Brazilian, Amazon, Android, Arts, major

    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
    æŀª
    -0.06
    çĤ
    -0.06
    çħĮ
    -0.06
    resh
    -0.06
    éĻµ
    -0.06
    çĤ¬
    -0.06
    次
    -0.06
    å¾Ĺ罪
    -0.06
    elli
    -0.06
    gne
    -0.05
    POSITIVE LOGITS
    zuk
    0.09
    iland
    0.09
    -runner
    0.08
    zÅij
    0.08
    getToken
    0.08
    ears
    0.08
    ç¡®ä¿Ŀå®īåħ¨
    0.07
    æĭ¥
    0.07
    veille
    0.07
    ÛĮزÛĮ
    0.07
    Activations Density 0.092%

    No Known Activations