© 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. 43315
    Prev
    Next
    INDEX
    Explanations

    preceded by control characters or quoted strings

    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
    ench
    -0.08
    ©
    -0.08
    妥å½ĵ
    -0.08
    rove
    -0.08
    untut
    -0.08
    icat
    -0.07
    ance
    -0.07
    à¹īà¸Ńม
    -0.07
    æī«äºĮç»´çłģ
    -0.07
    绿水éĿĴå±±
    -0.07
    POSITIVE LOGITS
     preceded
    0.07
    åģĩ
    0.06
    åĨł
    0.06
    akra
    0.06
     ÑĢаÑģпÑĢоÑģÑĤ
    0.06
    çīĩ
    0.06
    éĤĢ
    0.06
     Chall
    0.06
    ukum
    0.06
    abric
    0.06
    Activations Density 0.012%

    No Known Activations