© 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. 47962
    Prev
    Next
    INDEX
    Explanations

    understanding concepts

    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
    raries
    -0.11
    ìį¨
    -0.10
    olated
    -0.09
    assar
    -0.09
    IRTUAL
    -0.09
    ahaya
    -0.09
    ä¸įçĦ¶
    -0.08
    iated
    -0.08
    Ïĥη
    -0.08
     onDataChange
    -0.08
    POSITIVE LOGITS
    ness
    0.10
    ings
    0.09
    amental
    0.08
    HING
    0.08
    anza
    0.08
    à¸ģารà¸ĵà¹Į
    0.08
    brero
    0.07
    æŀģäºĨ
    0.07
    fulness
    0.07
    емо
    0.07
    Activations Density 0.037%

    No Known Activations