© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 871
    Prev
    Next
    INDEX
    Explanations

    templates, map, dose, cloned, data

    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
    eriop
    -0.08
    åħ¶éģĵ
    -0.08
    aeper
    -0.08
    zinho
    -0.08
    éºĴ
    -0.08
    ólog
    -0.08
    פ×ķר
    -0.08
     serii
    -0.08
    ЧиÑĤаÑĤÑĮ
    -0.08
     sourceMapping
    -0.07
    POSITIVE LOGITS
     preci
    0.06
     favors
    0.06
    åIJ¦
    0.06
    hei
    0.06
    éŃ
    0.06
     lek
    0.06
    éĺĻ
    0.06
    0.05
     Nicholson
    0.05
    è¯Ń
    0.05
    Activations Density 0.025%

    No Known Activations