© 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. 64523
    Prev
    Next
    INDEX
    Explanations

    hybrid circuits, gilded age, apocrine breast, omega-6 fatty, light flicker

    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
    è²Ķ
    -0.08
    ÑĤÑİ
    -0.08
    åı¤å±ĭ
    -0.08
    ombe
    -0.08
    ä¸įä½ıçļĦ
    -0.08
    cato
    -0.08
     Burgess
    -0.08
    aton
    -0.08
    ä¾µçĬ¯æĤ¨çļĦ
    -0.08
    ijos
    -0.08
    POSITIVE LOGITS
    oit
    0.07
     masc
    0.06
    "
    0.06
    示
    0.06
     mark
    0.06
    åĵĩ
    0.05
    éľľ
    0.05
     "
    0.05
    èĬ±çĶŁ
    0.05
    .
    0.05
    Activations Density 0.149%

    No Known Activations