© 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. 24182
    Prev
    Next
    INDEX
    Explanations

    always, usually, invariably, do

    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
    ulti
    -0.08
    inger
    -0.07
    Mgr
    -0.07
    åĢĴ
    -0.07
    éĶĻ误æĪĸ
    -0.07
     наконеÑĨ
    -0.07
     Off
    -0.07
    OULD
    -0.07
    abet
    -0.07
     finally
    -0.07
    POSITIVE LOGITS
    æĽ´ä½ķåĨµ
    0.11
    ä½ķåĨµ
    0.11
    \a
    0.07
    ellos
    0.07
     permalink
    0.07
    å½ĵåħ¶
    0.07
    ella
    0.06
    好åķĬ
    0.06
    ik
    0.06
    ä¸ĢèĪ¬éĥ½æĺ¯
    0.06
    Activations Density 0.100%

    No Known Activations