© 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. 24050
    Prev
    Next
    INDEX
    Explanations

    end of sentence question

    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
     (
    -0.06
    vers
    -0.06
    (
    -0.06
     rather
    -0.06
     Fou
    -0.06
     A
    -0.06
    eden
    -0.06
    aps
    -0.06
    udge
    -0.06
    ent
    -0.06
    POSITIVE LOGITS
    Õ»
    0.09
    åįĪ
    0.09
    rokes
    0.09
    liz
    0.08
    ãģĤãģĦ
    0.08
    ÑģÑĥди
    0.08
    æĻĤéĸĵãģ¯
    0.08
    æŶéĹ´åľ¨
    0.08
    uhl
    0.08
    lems
    0.08
    Activations Density 0.042%

    No Known Activations