© 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. 40415
    Prev
    Next
    INDEX
    Explanations

    numbers after parentheses

    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
    çĻ»
    -0.06
    jes
    -0.06
    Ga
    -0.06
    窥
    -0.06
    athers
    -0.06
    arring
    -0.06
    iston
    -0.06
     escalate
    -0.06
    æī©å¤§
    -0.06
    çĽĽå¤§çļĦ
    -0.06
    POSITIVE LOGITS
    .tm
    0.08
    phans
    0.07
    ompiler
    0.07
    éĻ¤å¤ĸ
    0.07
    伦å¤ļ
    0.07
    upert
    0.07
    æĭŃ缮
    0.07
     compiling
    0.07
    <|quad_start|>
    0.06
    èħ¾è®¯å¾®åįļ
    0.06
    Activations Density 0.031%

    No Known Activations