© 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. 63517
    Prev
    Next
    INDEX
    Explanations

    operation descriptor default

    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
    à¹Īวà¸ĩ
    -0.08
    ä¹ĭçĪ¶
    -0.07
    PFN
    -0.07
    åĬłå·¥å·¥èīº
    -0.07
    çĽĹ
    -0.07
    ili
    -0.07
    èĢĮå·²
    -0.06
    reif
    -0.06
    Docs
    -0.06
     preprocess
    -0.06
    POSITIVE LOGITS
    ervations
    0.08
    eball
    0.08
    å®īçIJª
    0.07
    ahun
    0.07
    ÑĬк
    0.07
    amia
    0.07
    æĸŃéĿ¢
    0.06
    gist
    0.06
    æľ«ä¸ĸ
    0.06
    åı°åİ¿
    0.06
    Activations Density 0.143%

    No Known Activations