© 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. 61533
    Prev
    Next
    INDEX
    Explanations

    really genuinely

    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
    Ø©
    -0.10
    uvres
    -0.10
    chnik
    -0.09
    и
    -0.08
    rotch
    -0.08
    ÌĢ
    -0.08
    edio
    -0.08
    羣å®ŀæĢ§è´Łè´£
    -0.08
    iop
    -0.08
    ierra
    -0.08
    POSITIVE LOGITS
    haft
    0.09
    nes
    0.08
    度çļĦ
    0.08
    hut
    0.08
    éĿ¢çĽ®
    0.08
    tr
    0.08
    اÙĭ
    0.07
    oe
    0.07
    era
    0.07
    hardt
    0.07
    Activations Density 0.005%

    No Known Activations