© 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. 50685
    Prev
    Next
    INDEX
    Explanations

    speed calculation

    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
    chst
    -0.08
     Presents
    -0.07
    שת
    -0.07
    æĵįä½ľè§Ħç¨ĭ
    -0.07
     налиÑĩ
    -0.07
    åĺ»
    -0.07
    landa
    -0.07
    æĥ¯äºĨ
    -0.07
    ковÑĮ
    -0.07
     kabul
    -0.07
    POSITIVE LOGITS
     mod
    0.08
    æ¯ĶæĻ®éĢļ
    0.07
    æĹ¥çħ§
    0.07
    åı¸
    0.07
    å´ĩ
    0.07
    wap
    0.07
    ило
    0.06
    温差
    0.06
    ickey
    0.06
    伪
    0.06
    Activations Density 0.006%

    No Known Activations