© 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. 19963
    Prev
    Next
    INDEX
    Explanations

    introduction sections

    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
    SError
    -0.07
    ازÙĩ
    -0.07
    ä¸įå·²
    -0.06
    urgia
    -0.06
    ulp
    -0.06
    ities
    -0.06
    åħ·æľīå¾Īé«ĺçļĦ
    -0.06
    áĥĶáĥł
    -0.06
    ÙĨاد
    -0.06
    _HAS
    -0.06
    POSITIVE LOGITS
    гнÑĥ
    0.07
    _UNIFORM
    0.07
    æĸ¯åŁº
    0.07
    guas
    0.07
    estad
    0.07
    ç§Ģ
    0.07
     YYS
    0.07
    gues
    0.07
    Ĭ
    0.07
    è§ģéĿ¢
    0.07
    Activations Density 0.186%

    No Known Activations