© 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. 24745
    Prev
    Next
    INDEX
    Explanations

    cricket runs past

    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
    iffs
    -0.08
    putc
    -0.08
    íĮIJ
    -0.07
    olla
    -0.07
    çıĪ
    -0.07
    ITLE
    -0.07
    ä¸Ģæ°Ķ
    -0.07
    IPP
    -0.07
    ÑĢоди
    -0.07
    igenza
    -0.07
    POSITIVE LOGITS
    åĺĽ
    0.08
    Ħ
    0.07
    åıĤä¸İè¯Ħ论
    0.07
    æĪijæĺ¯åľ¨
    0.07
    onel
    0.06
    åıĪä¸įæĺ¯
    0.06
    æľ¬æĿ¥æĺ¯
    0.06
    ment
    0.06
    ä¹°äºĨä¸Ģ
    0.06
    ilea
    0.06
    Activations Density 0.001%

    No Known Activations