© 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. 4064
    Prev
    Next
    INDEX
    Explanations

    ideal for, often faced, wide lock

    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
    plier
    -0.07
     Quest
    -0.07
    é«
    -0.07
     Plage
    -0.07
    elt
    -0.07
    .getOwnPropertyDescriptor
    -0.06
    ç´¢
    -0.06
    lish
    -0.06
    amburger
    -0.06
    getattr
    -0.06
    POSITIVE LOGITS
     multi
    0.15
     multic
    0.14
     multit
    0.13
    åľ¨å¤ļ
    0.12
    æĺ¯å¤ļ
    0.12
    Multi
    0.12
     обÑĬединениÑı
    0.12
     aggreg
    0.12
     aggregation
    0.12
     multin
    0.12
    Activations Density 0.533%

    No Known Activations