© 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. 13503
    Prev
    Next
    INDEX
    Explanations

    construction of

    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
    oor
    -0.08
    Ł
    -0.08
    第ä¸Ģ大
    -0.08
    çĪĨæ£ļ
    -0.08
    avanaugh
    -0.08
    ÙĪضة
    -0.08
    izer
    -0.08
    /frame
    -0.08
    ovice
    -0.07
    ool
    -0.07
    POSITIVE LOGITS
     ined
    0.07
    heen
    0.06
    Ùĩ
    0.06
     schad
    0.06
    ichel
    0.06
    精巧
    0.06
    èĥĨåŃIJ
    0.06
    ä¸İåĪĨæŀIJ
    0.06
    vit
    0.06
    ttes
    0.06
    Activations Density 0.001%

    No Known Activations