© 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. 65056
    Prev
    Next
    INDEX
    Explanations

    mathematical expressions rearrange

    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
     Lafayette
    -0.07
    ezz
    -0.07
    aille
    -0.07
    udan
    -0.07
    ands
    -0.07
    uple
    -0.06
    ýt
    -0.06
     Gradu
    -0.06
    udge
    -0.06
    ookie
    -0.06
    POSITIVE LOGITS
    iesel
    0.07
    çĽ¸ä¼¼æĸĩçĮ®
    0.07
    |-
    0.07
     кип
    0.07
    _|
    0.07
    citation
    0.07
    itele
    0.06
    ataloader
    0.06
    umat
    0.06
    è°ĥæŁ¥æĬ¥åijĬ
    0.06
    Activations Density 0.228%

    No Known Activations