© 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. 46954
    Prev
    Next
    INDEX
    Explanations

    statement to, ago when, sent Toronto

    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
    aveur
    -0.10
    etro
    -0.08
    ähr
    -0.08
    æį
    -0.08
    ä¸ĬåѦ
    -0.08
    rome
    -0.08
    ãĥ¼ãĤ¹
    -0.08
     berin
    -0.08
    ä¸Ĭå±±
    -0.08
    ROME
    -0.08
    POSITIVE LOGITS
    jan
    0.07
    大éħĴåºĹ
    0.06
    colon
    0.06
    ouser
    0.06
    zio
    0.06
    ikut
    0.06
     er
    0.06
     Curt
    0.05
    æµ·æ¶Ľ
    0.05
    師
    0.05
    Activations Density 0.139%

    No Known Activations