© 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. 25670
    Prev
    Next
    INDEX
    Explanations

    as implying or indicating

    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
     KeyboardInterrupt
    -0.07
    uva
    -0.07
    HTTPRequest
    -0.07
    ãģ©ãĤĬ
    -0.06
    å±ħæĺĵ
    -0.06
    álu
    -0.06
    ÃŃna
    -0.06
    鼰
    -0.06
    OTH
    -0.06
    oges
    -0.06
    POSITIVE LOGITS
     necessarily
    0.10
     necesariamente
    0.08
    à¹Ģà¸Ĭิà¸ĩ
    0.08
    å°±ä¸Ģå®ļ
    0.08
     somehow
    0.07
    endors
    0.07
    å®ŀéĻħ
    0.07
     ÑģобÑģÑĤвенно
    0.07
    sted
    0.07
     sebenarnya
    0.07
    Activations Density 0.135%

    No Known Activations