© 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. 29467
    Prev
    Next
    INDEX
    Explanations

    punctuation and subsequent words

    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
     dig
    -0.08
    klus
    -0.07
    amat
    -0.07
    Dig
    -0.07
    为好åıĭ
    -0.07
     Dig
    -0.07
     Matr
    -0.07
    opf
    -0.07
    ÃģC
    -0.07
    çħĮ
    -0.07
    POSITIVE LOGITS
    æī©å±ķèµĦæĸĻ
    0.07
    cord
    0.07
    é£ĺ
    0.07
    å½ĵä¸ŃçļĦ
    0.07
    oki
    0.07
    yne
    0.07
    alap
    0.07
    _timing
    0.06
    ttore
    0.06
     frem
    0.06
    Activations Density 0.584%

    No Known Activations