© 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. 39419
    Prev
    Next
    INDEX
    Explanations

    regular

    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
    ä»
    -0.08
    getError
    -0.08
    çĻ¾å¿Ļ
    -0.07
    ÑĢик
    -0.07
    ulous
    -0.07
    åĢ¼æѤ
    -0.07
    ко
    -0.07
    leans
    -0.07
    HEST
    -0.07
    LBL
    -0.07
    POSITIVE LOGITS
     sooner
    0.07
    æīįæľīåı¯èĥ½
    0.07
     eventually
    0.07
     altogether
    0.07
     necessarily
    0.07
    ãĥļãĥ¼ãĤ¹
    0.06
     Must
    0.06
    must
    0.06
    è¦ģèĢĥèĻij
    0.06
     Downs
    0.06
    Activations Density 0.031%

    No Known Activations