© 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. 33867
    Prev
    Next
    INDEX
    Explanations

    clear and descriptive writing

    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
    ailles
    -0.08
    orial
    -0.08
    apus
    -0.07
    èı²çī¹
    -0.07
    illo
    -0.07
    EQUAL
    -0.07
    -delete
    -0.07
    anka
    -0.07
    ero
    -0.07
    utz
    -0.07
    POSITIVE LOGITS
    åıĪä¸Ģ
    0.07
    omers
    0.07
    è¿Ļ便æĺ¯
    0.06
    大æĸ¹çļĦ
    0.06
    æĮ¯åįİ
    0.06
     vX
    0.06
    λικ
    0.06
    ван
    0.06
    å¾ħåľ¨
    0.06
    ëħ¹
    0.06
    Activations Density 0.003%

    No Known Activations