© 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. 22970
    Prev
    Next
    INDEX
    Explanations

    Nay?

    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
    ehl
    -0.08
    zni
    -0.07
    çĥŃè¡Ģ沸èħ¾
    -0.07
    еÑĢбÑĥ
    -0.07
    ç®Ģ称
    -0.07
    aris
    -0.07
    å¯ĦãģĽ
    -0.07
    æ·¡æ·¡
    -0.07
    arus
    -0.07
    _Il
    -0.07
    POSITIVE LOGITS
    ä¼ij
    0.07
    stv
    0.07
    åħ¼
    0.07
    mie
    0.06
    强
    0.06
    ATS
    0.06
    èĥŀ
    0.06
    æıIJè´¨
    0.06
    ç«ł
    0.06
    æ·»
    0.06
    Activations Density 0.062%

    No Known Activations