© 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. 29016
    Prev
    Next
    INDEX
    Explanations

    a list, explanation, concise, new

    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
    elper
    -0.07
    ิว
    -0.07
     famously
    -0.07
    éĻIJäºİ
    -0.07
    acao
    -0.07
     bestimm
    -0.07
    é¢ĩå¤ļ
    -0.07
    idth
    -0.07
    çŀ³
    -0.07
     bepaalde
    -0.07
    POSITIVE LOGITS
     examples
    0.09
     ourselves
    0.09
     ways
    0.08
     reasoning
    0.08
     illustration
    0.07
    ä¾ĭåŃIJ
    0.07
     proof
    0.07
     overview
    0.07
     explanation
    0.07
     concise
    0.07
    Activations Density 0.074%

    No Known Activations