© 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. 18209
    Prev
    Next
    INDEX
    Explanations

    met ref B

    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
    å¸Ń
    -0.08
    vik
    -0.07
    iat
    -0.07
    ä¼ij
    -0.07
    èįIJ
    -0.07
    çĸ¼
    -0.06
    ansa
    -0.06
    æŀķ
    -0.06
    etwork
    -0.06
    ccion
    -0.06
    POSITIVE LOGITS
    ght
    0.08
    ä»ħæѤ
    0.07
    izon
    0.07
    ingend
    0.07
    losures
    0.07
    ä¸įçŁ¥æīĢ
    0.07
    社éķ¿
    0.07
    кло
    0.07
    gba
    0.07
    воÑĢоÑĤ
    0.07
    Activations Density 0.075%

    No Known Activations