© 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. 23002
    Prev
    Next
    INDEX
    Explanations

    numbers and codes

    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
    -tool
    -0.07
    onna
    -0.07
    itu
    -0.06
    é¹ĥ
    -0.06
    wi
    -0.06
    urt
    -0.06
    нга
    -0.06
    rot
    -0.06
    å½ĵäºĭ
    -0.06
    amar
    -0.06
    POSITIVE LOGITS
    ordat
    0.08
    atakan
    0.07
    ê¼
    0.07
    æĹıèĩªæ²»åİ¿
    0.07
    :Number
    0.07
    elado
    0.07
    icei
    0.07
    ainya
    0.07
    okies
    0.07
    åħ¬åı¸æݨèįIJ
    0.07
    Activations Density 0.194%

    No Known Activations