© 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. 26282
    Prev
    Next
    INDEX
    Explanations

    q, Q, QQ

    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
     اÛĮÙĨÚ©Ùĩ
    -0.09
    jenigen
    -0.08
    çĴĢ
    -0.08
    ÑģÑĤеÑĢ
    -0.08
     volna
    -0.08
    ÑģÑĤе
    -0.08
    rhein
    -0.08
    ohner
    -0.08
    edio
    -0.08
    uj
    -0.08
    POSITIVE LOGITS
    itative
    0.11
    ubit
    0.10
    rcode
    0.10
    pedia
    0.09
    estion
    0.09
    unque
    0.09
    ubits
    0.09
    ingly
    0.08
    CoreApplication
    0.08
    manship
    0.08
    Activations Density 0.654%

    No Known Activations