© 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. 62757
    Prev
    Next
    INDEX
    Explanations

    horizontal and vertical directions

    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
    º
    -0.10
    emming
    -0.09
    zyb
    -0.09
    ÑĤиÑĤ
    -0.08
     Diagnos
    -0.08
    éĢħ
    -0.08
    intis
    -0.08
    ниÑĨей
    -0.08
    leon
    -0.08
    ÑĨеÑĢ
    -0.08
    POSITIVE LOGITS
     vertical
    0.07
    åħ¬éģĵ
    0.06
     aiding
    0.06
    æī¶
    0.06
    ç«ĸ缴
    0.06
    ↵
    0.06
    éĿ¢åIJij
    0.06
    å·¥åķĨè¡ĮæĶ¿ç®¡çIJĨå±Ģ
    0.06
     assisting
    0.06
     envol
    0.06
    Activations Density 0.010%

    No Known Activations