© 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. 48660
    Prev
    Next
    INDEX
    Explanations

    genotype variants (homo/hetero)

    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
    amik
    -0.07
    oola
    -0.07
    ẩn
    -0.07
    _LOC
    -0.06
    Loop
    -0.06
    antha
    -0.06
    _AM
    -0.06
    åĪģ
    -0.06
    زش
    -0.06
     Loop
    -0.06
    POSITIVE LOGITS
     genotype
    0.09
    eliz
    0.08
    YP
    0.08
    à¸ĵà¹Į
    0.08
    éĥİ
    0.08
     combinations
    0.08
    ç»ıèIJ¥çĬ¶æĢģ
    0.07
    è¯ģæį®è¯ģæĺİ
    0.07
     individuals
    0.07
    iche
    0.07
    Activations Density 0.014%

    No Known Activations