© 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. 10755
    Prev
    Next
    INDEX
    Explanations

    general solutions

    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
    èĭ¦
    -0.08
    åŃĺ
    -0.07
    rid
    -0.07
    ä¿¡æģ¯ç½ij
    -0.07
    ife
    -0.07
    ellig
    -0.07
    erra
    -0.06
    hest
    -0.06
    æŀĦ
    -0.06
    room
    -0.06
    POSITIVE LOGITS
    ariana
    0.08
    jukan
    0.08
    omia
    0.07
    è¿Ļ个åĽŀçŃĶ
    0.07
    anding
    0.07
    èĭ±ä¿Ĭ
    0.07
    arcz
    0.07
    人士表示
    0.07
    à¥įला
    0.07
    缴è§Ĥ
    0.07
    Activations Density 0.007%

    No Known Activations