© 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. 48700
    Prev
    Next
    INDEX
    Explanations

    iterator and loop constructs

    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
     aspiring
    -0.06
    atics
    -0.06
    Âł
    -0.06
    ulu
    -0.06
    здÑĢа
    -0.06
    rum
    -0.06
    :Int
    -0.06
    anggung
    -0.06
    apel
    -0.06
    èĦļè¸ıå®ŀåľ°
    -0.06
    POSITIVE LOGITS
    retta
    0.08
    éĽĢ
    0.08
    ential
    0.07
    bbie
    0.07
    refix
    0.07
     Fires
    0.07
    Õ¥Õ¶
    0.07
    rah
    0.07
    åĵ¨
    0.07
    ล
    0.07
    Activations Density 0.018%

    No Known Activations