© 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. 20934
    Prev
    Next
    INDEX
    Explanations

    past events or states

    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
    Âł
    -0.08
    ies
    -0.08
    er
    -0.07
    æĺ¯èĥ½
    -0.07
    ish
    -0.06
    elia
    -0.06
    ie
    -0.06
    ber
    -0.06
    å½¼
    -0.06
     vs
    -0.06
    POSITIVE LOGITS
    aleb
    0.09
    PIO
    0.08
    æ²½
    0.08
    çŀ°
    0.08
    icans
    0.08
    auff
    0.08
    à¤ŀ
    0.08
    为åIJĮåѦ们
    0.08
    reib
    0.08
    é¼
    0.08
    Activations Density 0.076%

    No Known Activations