© 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. 51074
    Prev
    Next
    INDEX
    Explanations

    vitamins and magnesium

    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
    åIJĮæŶè¿ĺè¦ģ
    -0.08
    æ£Ģæµĭç»ĵæŀľ
    -0.08
    鼶è·Ŀ离
    -0.08
    ceau
    -0.08
    羣å¿ĥçļĦ
    -0.08
    eus
    -0.08
    ByExample
    -0.08
    产æĿĥæĪ¿
    -0.08
    presso
    -0.07
     Arbitrary
    -0.07
    POSITIVE LOGITS
    Âł
    0.07
    åij³çĶĺ
    0.07
    /action
    0.06
    å¾®
    0.06
    nes
    0.06
    次
    0.06
    ubes
    0.06
    èµĭ
    0.06
    oke
    0.06
    ä¸Ģ级
    0.06
    Activations Density 0.008%

    No Known Activations