© 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. 1297
    Prev
    Next
    INDEX
    Explanations

    indices and sequences

    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
    er
    -0.09
    o
    -0.09
    edom
    -0.08
    erden
    -0.08
    ¤
    -0.08
    cular
    -0.07
    bsites
    -0.07
    ½
    -0.07
    pared
    -0.07
    psilon
    -0.07
    POSITIVE LOGITS
    ingly
    0.09
    ivery
    0.08
    ุà¸Ļ
    0.08
    Allem
    0.08
    ingleton
    0.08
    ipse
    0.08
    ungsk
    0.07
    iability
    0.07
    æĪij们èĥ½å¤Ł
    0.07
    ively
    0.07
    Activations Density 0.009%

    No Known Activations