© 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. 56694
    Prev
    Next
    INDEX
    Explanations

    thereby, thus, consequently

    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
    å¾Ĺ天çĭ¬
    -0.07
     наÑģÑĤолÑĮко
    -0.07
    为äºĨç¡®ä¿Ŀ
    -0.06
    ska
    -0.06
    ohl
    -0.06
    åľ¨å®ĥ
    -0.06
    ¥
    -0.06
    éģĩåĪ°äºĨ
    -0.06
    å±ķæľĽ
    -0.06
    mar
    -0.06
    POSITIVE LOGITS
     thus
    0.10
    /or
    0.09
     thereby
    0.09
    ä»İèĢĮ
    0.08
    /OR
    0.08
     therefore
    0.08
     consequently
    0.08
    åĽłæŃ¤åľ¨
    0.08
    åĽłæѤ
    0.08
    ä¹Łå°±
    0.08
    Activations Density 0.206%

    No Known Activations