© 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. 33188
    Prev
    Next
    INDEX
    Explanations

    computer, medical, math, programming, science

    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
    roken
    -0.07
    issan
    -0.06
     down
    -0.06
     demon
    -0.06
    educt
    -0.06
     pu
    -0.06
     pur
    -0.06
    ä¸ĢåĪ°
    -0.06
    æ³°
    -0.06
     Forbes
    -0.05
    POSITIVE LOGITS
    èĥ¤
    0.08
    gau
    0.08
    mans
    0.08
    eler
    0.08
    stream
    0.08
    rial
    0.08
    PIPE
    0.07
    egi
    0.07
    zugehen
    0.07
    _DECLS
    0.07
    Activations Density 1.285%

    No Known Activations