© 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. 11198
    Prev
    Next
    INDEX
    Explanations

    before I

    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
    endr
    -0.07
    end
    -0.06
    ä½Ĩä¸įæĺ¯
    -0.06
    then
    -0.06
    ä»ĸåij½
    -0.06
    æľĢç»Ī以
    -0.06
    èĨ³é£Ł
    -0.06
     otherwise
    -0.06
    fet
    -0.06
     Lust
    -0.06
    POSITIVE LOGITS
     previa
    0.09
    -faced
    0.09
    åħĪæĿ¥
    0.08
    leti
    0.08
    åħĪ
    0.08
    backs
    0.08
    letz
    0.07
     terlebih
    0.07
     ÙĪÙĤبÙĦ
    0.07
    culares
    0.07
    Activations Density 0.008%

    No Known Activations