© 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. 13963
    Prev
    Next
    INDEX
    Explanations

    discussion/information sections

    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
    _blocked
    -0.08
    æĩĴ
    -0.07
    acie
    -0.07
    _HERE
    -0.07
    egro
    -0.07
    uket
    -0.06
    каи
    -0.06
    (-(
    -0.06
    Trim
    -0.06
    _erase
    -0.06
    POSITIVE LOGITS
     exponent
    0.08
    iram
    0.07
    itch
    0.07
    _resolver
    0.07
    endra
    0.07
    åľĥ
    0.07
    è·
    0.07
    /math
    0.07
    çļĦæīĭæĮĩ
    0.07
     expon
    0.06
    Activations Density 0.001%

    No Known Activations