© 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. 50443
    Prev
    Next
    INDEX
    Explanations

    numbers and variables

    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
    æĭīåħĭ
    -0.08
    μάÏĦÏīν
    -0.07
    erman
    -0.07
    adang
    -0.07
    éŁ³åĥı
    -0.07
    enson
    -0.07
    åĴĮå¹³
    -0.06
    èĩ´ä»¥
    -0.06
    éĥİ
    -0.06
    å½Ĵ
    -0.06
    POSITIVE LOGITS
    æģķ
    0.07
    çĶļèĩ³æĺ¯
    0.07
    cire
    0.07
    æĪĸ以ä¸Ĭ
    0.07
    åIJĮè¡Įä¸ļ
    0.07
    azel
    0.06
    çĬ¯
    0.06
    ä¸įèĥľæķ°
    0.06
    ä»Ĩ
    0.06
    èĢĢ
    0.06
    Activations Density 0.005%

    No Known Activations