© 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. 64324
    Prev
    Next
    INDEX
    Explanations

    `shared_ptr` or `RefPtr`

    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
    opportun
    -0.07
    оÑĢи
    -0.07
    ész
    -0.07
    oport
    -0.07
     rendez
    -0.07
    éĩĩ访ä¸Ń
    -0.07
     Jewel
    -0.07
     Wich
    -0.07
    illa
    -0.07
    arien
    -0.07
    POSITIVE LOGITS
    ä¸įæŃ»
    0.08
    ัà¸ļ
    0.08
    uth
    0.08
    uther
    0.07
    iss
    0.07
    edir
    0.06
    ìĤ´
    0.06
    竹åı¶
    0.06
    emer
    0.06
    代
    0.06
    Activations Density 0.088%

    No Known Activations