© 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. 20155
    Prev
    Next
    INDEX
    Explanations

    generalize, generic,

    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
    大åĮħ
    -0.07
    åħ»
    -0.07
    iche
    -0.07
    ä¸įæīĵ
    -0.06
    _specific
    -0.06
     Harmony
    -0.06
    gable
    -0.06
    åIJĪä½ľçĶ¨
    -0.06
    èµĭ
    -0.06
    дика
    -0.06
    POSITIVE LOGITS
     generalize
    0.14
     generalized
    0.12
     general
    0.11
    /general
    0.11
     generic
    0.11
    general
    0.11
    -general
    0.11
    éĢļçĶ¨
    0.11
    çļĦä¸ĢèĪ¬
    0.10
    Generic
    0.10
    Activations Density 0.155%

    No Known Activations