© 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. 29484
    Prev
    Next
    INDEX
    Explanations

    plus signs preceding letters or symbols

    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
    es
    -0.12
    er
    -0.09
    en
    -0.09
    erin
    -0.09
    an
    -0.09
    et
    -0.08
    ed
    -0.07
    à¥ĩ
    -0.07
    aÄĩ
    -0.07
    aient
    -0.07
    POSITIVE LOGITS
    hood
    0.09
    á»ĥn
    0.09
    cito
    0.08
    हार
    0.08
    رÙģ
    0.08
    onical
    0.08
    jdbc
    0.08
    landet
    0.08
    ÙĦاع
    0.08
    uids
    0.08
    Activations Density 0.004%

    No Known Activations