© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 63972
    Prev
    Next
    INDEX
    Explanations

    list structure elements

    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
    çªĺ
    -0.06
    éij«
    -0.06
     sil
    -0.05
     border
    -0.05
     standalone
    -0.05
     agr
    -0.05
    -,
    -0.05
     Nan
    -0.05
    OrUpdate
    -0.05
    å¦Ĥåħ¶
    -0.05
    POSITIVE LOGITS
     übers
    0.08
    ewise
    0.08
    rences
    0.07
    rede
    0.07
    å¿«å¿«ä¹IJ
    0.07
    azos
    0.07
    arge
    0.07
    à¹Ħà¸Ĥ
    0.07
    æĢİ麼辦
    0.07
    çļĦèĩªå·±
    0.07
    Activations Density 0.007%

    No Known Activations