© 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. 41836
    Prev
    Next
    INDEX
    Explanations

    analysis of spinal muscular atrophy

    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
    ä¸įå¼ĥ
    -0.08
    cluded
    -0.08
    iguez
    -0.08
    æīĭåı¯
    -0.07
    manos
    -0.07
    onden
    -0.07
    ierzch
    -0.07
    åŃĹè¯į
    -0.07
    uelle
    -0.07
    ä½Ł
    -0.07
    POSITIVE LOGITS
     dek
    0.07
    èĢĮä¸Ķæĺ¯
    0.07
     Mint
    0.06
    çĽ
    0.06
    asm
    0.06
    iv
    0.06
    å¨Ħ
    0.06
    hun
    0.06
    å¾®
    0.06
    ata
    0.06
    Activations Density 0.942%

    No Known Activations