© 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. 58215
    Prev
    Next
    INDEX
    Explanations

    worn accessories

    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
    ather
    -0.06
    ä¸įèĩ³
    -0.06
     relevant
    -0.06
    å¹³æĹ¥éĩĮ
    -0.06
    æķ¦
    -0.05
    ×Ĺ×ķת
    -0.05
    æ±²
    -0.05
    “
    -0.05
    ër
    -0.05
    _INIT
    -0.05
    POSITIVE LOGITS
    wszy
    0.09
    éĩijæ¦ľ
    0.08
    -addon
    0.08
    astas
    0.08
    åIJįåŃĹåı«
    0.07
    uruh
    0.07
    anjang
    0.07
    æĽĻ
    0.07
    _enqueue
    0.07
    åİĤå®¶çĽ´éĶĢ
    0.07
    Activations Density 0.123%

    No Known Activations