© 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. 2169
    Prev
    Next
    INDEX
    Explanations

    greatest common divisor, lowest common multiple

    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
    çģ£
    -0.08
    obe
    -0.07
    ly
    -0.07
    .eng
    -0.06
    æļ´é£İ鼨
    -0.06
    æŀ¯èIJİ
    -0.06
    ged
    -0.06
    ĩ
    -0.06
    ukan
    -0.06
     rud
    -0.06
    POSITIVE LOGITS
    ypes
    0.09
    leftright
    0.08
    ีม
    0.08
    ловиÑĩ
    0.08
    LOCKS
    0.08
    plib
    0.08
    åĪ°çĽ®åīį
    0.08
    ichten
    0.08
    @gmail
    0.08
    ocket
    0.08
    Activations Density 0.242%

    No Known Activations