© 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. 29680
    Prev
    Next
    INDEX
    Explanations

    categories and classifications (type, subtype, group, stage, week, site, cell, layer)

    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
    俱ä¹IJéĥ¨
    -0.07
    rf
    -0.07
    xd
    -0.06
    cp
    -0.06
    ï¸İ
    -0.06
    ra
    -0.06
    quel
    -0.06
    rd
    -0.06
    oo
    -0.06
    syl
    -0.06
    POSITIVE LOGITS
    sthrough
    0.09
    à¸Ńืà¹Īà¸Ļ
    0.09
    们éĥ½
    0.08
    ানà§įত
    0.08
    zilla
    0.08
    (es
    0.08
    sth
    0.08
    -specific
    0.08
    onna
    0.08
    stagram
    0.08
    Activations Density 0.140%

    No Known Activations