© 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. 65207
    Prev
    Next
    INDEX
    Explanations

    algebraic complexity field

    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
    oncini
    -0.08
    ekom
    -0.08
    á»ĩt
    -0.08
     ÑĦаÑģ
    -0.07
    ohl
    -0.07
    èªī
    -0.07
    åĨħ设
    -0.07
    atham
    -0.06
    tures
    -0.06
    çĻ¾èįī
    -0.06
    POSITIVE LOGITS
    éħ¿éħĴ
    0.09
     tess
    0.08
    ria
    0.08
    æ¬Ħ
    0.07
    ienst
    0.07
    è¯ģ书
    0.07
    ieber
    0.07
    пиÑı
    0.07
    _DLL
    0.07
    磮
    0.07
    Activations Density 0.005%

    No Known Activations