© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 30156
    Prev
    Next
    INDEX
    Explanations

    accounting for

    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
    -0.08
    er
    -0.08
     dÃłng
    -0.08
    estra
    -0.08
    غÙĦ
    -0.07
    æł·çļĦ
    -0.07
    /her
    -0.07
    earch
    -0.07
    uctions
    -0.07
    vende
    -0.07
    POSITIVE LOGITS
    enance
    0.11
    à¸ģารà¸ĵà¹Į
    0.10
    edly
    0.09
    iveness
    0.08
    ../../
    0.08
    å¾Ĺä¸Ĭ
    0.08
    ably
    0.08
    à¸Ħรัว
    0.08
    itude
    0.08
    ronym
    0.08
    Activations Density 0.033%

    No Known Activations