© 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. 43772
    Prev
    Next
    INDEX
    Explanations

    names starting with D, M, I

    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
    åıªå¯¹
    -0.08
    çĭłæĬĵ
    -0.07
    ä¸įè°ĥ
    -0.06
    诧
    -0.06
    åĪĢ
    -0.06
    åĵ®
    -0.06
    olas
    -0.06
     اÙĦØ«ÙĤ
    -0.06
    缴æݥ影åĵįåĪ°
    -0.05
     surve
    -0.05
    POSITIVE LOGITS
    omen
    0.09
    serter
    0.08
    çº
    0.08
    omini
    0.08
     **:**
    0.08
    colar
    0.08
    íݸ
    0.07
    psilon
    0.07
    BlockSize
    0.07
    cop
    0.07
    Activations Density 0.070%

    No Known Activations