© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 15102
    Prev
    Next
    INDEX
    Explanations

    default option

    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
    ?type
    -0.09
    åķĨæĬ¥
    -0.08
    еÑģе
    -0.07
    ÙĬØŃ
    -0.07
    _FORWARD
    -0.07
     misk
    -0.07
    ç¦ģåĮº
    -0.07
    pong
    -0.07
     Pearce
    -0.07
    以ä¸ĭçļĦç½ļ款
    -0.07
    POSITIVE LOGITS
    é»ĺ认
    0.08
     assumption
    0.08
    default
    0.07
    为äºĨ满足
    0.07
    åģĩ设
    0.07
    å¦Ĵ
    0.07
    generic
    0.07
     default
    0.07
    çĮĽ
    0.07
    _default
    0.07
    Activations Density 0.021%

    No Known Activations