© 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. 37828
    Prev
    Next
    INDEX
    Explanations

    reuse, repeat, common features

    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
    ugen
    -0.08
    éĻĩ
    -0.07
    itel
    -0.07
    ãģĤãģı
    -0.07
    HING
    -0.07
    åĽĽçݯ
    -0.07
    alah
    -0.06
    éĵĽ
    -0.06
    chow
    -0.06
    ÑģÑĤÑĥпа
    -0.06
    POSITIVE LOGITS
     reusable
    0.14
    ä¸įçĶ¨åĨį
    0.13
     repetitive
    0.13
    èĬĤçľģ
    0.12
     reuse
    0.12
    Reusable
    0.12
    éĩįå¤į
    0.12
    Repeated
    0.12
    Reuse
    0.12
     repeated
    0.12
    Activations Density 0.367%

    No Known Activations