© 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. 9103
    Prev
    Next
    INDEX
    Explanations

    time duration units

    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
    äºijéĽĨ
    -0.07
    rilla
    -0.07
    åĬłç´¢
    -0.07
    arz
    -0.07
     Pistol
    -0.07
    ÑĤÑĥÑģ
    -0.07
    ×ķ×ķ
    -0.07
    mann
    -0.07
    alii
    -0.07
    atsu
    -0.07
    POSITIVE LOGITS
     elapsed
    0.07
    _extra
    0.07
    缴è¾ĸ
    0.07
    åī©ä½ĻçļĦ
    0.07
    è¶ħéķ¿
    0.06
    æķ´
    0.06
    GPS
    0.06
    Elapsed
    0.06
     duration
    0.06
    ahr
    0.06
    Activations Density 0.028%

    No Known Activations