© 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. 12526
    Prev
    Next
    INDEX
    Explanations

    genotype alleles

    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
     ABOVE
    -0.08
    以ä¸ĬåĨħ容
    -0.08
    APT
    -0.08
    ä¸Ĭä¸Ģå±Ĥ楼
    -0.08
    rane
    -0.07
    onor
    -0.07
    åĶĨ
    -0.07
    rados
    -0.07
    éĺ³åĮº
    -0.06
    è¿ľè¶ħ
    -0.06
    POSITIVE LOGITS
    ä¸įåłª
    0.09
    å¾Īä½İ
    0.09
    çģ°å¿ĥ
    0.08
    æĽ´ä½İ
    0.08
    à¸Ķà¹īาà¸Ļลà¹Īาà¸ĩ
    0.08
    累累
    0.08
    .none
    0.08
     thấp
    0.08
    éĢĨè¢Ń
    0.08
    è°·åºķ
    0.08
    Activations Density 0.004%

    No Known Activations