© 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. 38419
    Prev
    Next
    INDEX
    Explanations

    fail, mischief, deficient, failed, rises, leak

    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
    ikal
    -0.07
    åĽ¾æĸ¯
    -0.07
     бÑĥдÑĥÑīего
    -0.07
    æ·¡
    -0.07
    istem
    -0.07
    harmon
    -0.07
    ekom
    -0.07
    idl
    -0.07
    _FIX
    -0.07
    è´µéĩį
    -0.07
    POSITIVE LOGITS
    ä¸įåłª
    0.08
    ä½ĨåıĪ
    0.08
    秽
    0.07
    潦
    0.07
    åĬłåī§
    0.07
    ä¸įä¼ij
    0.07
    æīĵçł´
    0.06
    åį§åºĬ
    0.06
    饥饿
    0.06
    /null
    0.06
    Activations Density 0.130%

    No Known Activations