© 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. 2632
    Prev
    Next
    INDEX
    Explanations

    study outcomes and results

    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
    edBy
    -0.07
    ä½Ĩè¿Ļ个
    -0.07
     =>
    -0.06
    tria
    -0.06
    åĩºèº«çļĦ
    -0.06
    éĤ£ä¹Īè¿Ļ个
    -0.06
    èĢĮè¿Ļ个
    -0.06
    åĽłæĿIJ
    -0.06
    eyond
    -0.06
    pq
    -0.06
    POSITIVE LOGITS
     consisted
    0.10
    RESULTS
    0.09
     herein
    0.08
    以ä¸ĭåĨħ容
    0.08
    .RESULT
    0.08
    为äºĨèĥ½
    0.08
    was
    0.08
    .Results
    0.07
    æ¯ı天æĹ©ä¸Ĭ
    0.07
     Sect
    0.07
    Activations Density 0.610%

    No Known Activations