© 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. 13374
    Prev
    Next
    INDEX
    Explanations

    units, circuit, facility, hat, child

    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
    onta
    -0.08
    ÑĨиа
    -0.08
    ONIO
    -0.07
    UTA
    -0.07
    INSTANCE
    -0.07
    μία
    -0.07
    NetMessage
    -0.07
    avn
    -0.07
    羣å¿ĥ
    -0.07
    ç»Ļå®Ŀå®Ŀ
    -0.07
    POSITIVE LOGITS
    eg
    0.08
     eg
    0.07
    éĹŃ
    0.07
    zeitig
    0.07
    å²Ĺ
    0.07
    é¢Ŀ
    0.06
    ereg
    0.06
    sink
    0.06
     getCurrent
    0.06
    ä½ĵ
    0.06
    Activations Density 0.641%

    No Known Activations