© 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. 46959
    Prev
    Next
    INDEX
    Explanations

    or, with, or, with

    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
     à¸ŀà¸¤à¸©à¸łà¸²à¸Ħม
    -0.06
     abstract
    -0.06
    ilos
    -0.06
    æ²Ĥ
    -0.06
    åħ¥
    -0.06
    est
    -0.06
    æĬ½è±¡
    -0.06
    åij¨èº«
    -0.06
    æľ¬åĽŀçŃĶ
    -0.06
    ä¸įæĢĿ
    -0.06
    POSITIVE LOGITS
    ellan
    0.08
    ç¨įç¨į
    0.08
    łíĮ
    0.08
     nasional
    0.08
    çķ¥æľī
    0.08
    ganos
    0.08
    æł¹æį®ä¸ªäºº
    0.08
    ä¸įéĤ£ä¹Ī
    0.08
    tral
    0.08
    бли
    0.08
    Activations Density 0.128%

    No Known Activations