© 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. 31688
    Prev
    Next
    INDEX
    Explanations

    as shown, compared, opposed, well, recently

    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
    ä¸Ģä½ľ
    -0.09
    éĿĴäºij
    -0.09
    ä¸īæĽ´
    -0.09
    landa
    -0.08
    ãĤıãĤĬãģ«
    -0.08
    ÑĢавни
    -0.08
    unesse
    -0.08
    took
    -0.08
    бÑĥдÑĮ
    -0.08
    starts
    -0.08
    POSITIVE LOGITS
     evidenced
    0.09
    è§ģäºİ
    0.08
     demonstrated
    0.07
    iam
    0.07
     exempl
    0.07
     practiced
    0.07
    IJ
    0.06
    piring
    0.06
     illustrated
    0.06
     in
    0.06
    Activations Density 0.135%

    No Known Activations