© 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. 9069
    Prev
    Next
    INDEX
    Explanations

    phonebook, error-establishing, faceapp

    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¸Ľà¸±
    -0.08
    abora
    -0.07
    æħķå°¼é»ij
    -0.07
    åt
    -0.07
    вани
    -0.06
    èv
    -0.06
    大马
    -0.06
    马è¹Ħ
    -0.06
    zana
    -0.06
     pomp
    -0.06
    POSITIVE LOGITS
    è¿Ļæł·è¯´
    0.08
    è¿Ļä¹Ī说
    0.08
    ',//
    0.08
    æĺ¯è¿Ļæł·çļĦ
    0.07
     Tuch
    0.07
    çĶŁåij½ä¸ŃçļĦ
    0.07
     ifdef
    0.07
    æľīè¿Ļæł·çļĦ
    0.07
    æĺ¥æļĸ
    0.07
    alik
    0.07
    Activations Density 0.002%

    No Known Activations