© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 48235
    Prev
    Next
    INDEX
    Explanations

    declaration statements

    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
    -0.09
    whatever
    -0.07
    æĸĩåĩŃ
    -0.07
    umbo
    -0.07
    à¤Ĥत
    -0.07
     Lilly
    -0.07
    icus
    -0.07
     Adi
    -0.06
    _UNSUPPORTED
    -0.06
    ungi
    -0.06
    POSITIVE LOGITS
    oure
    0.07
    åįĹéŨ
    0.07
    agle
    0.07
    immer
    0.07
     themselves
    0.07
    ีม
    0.07
    angan
    0.07
    utc
    0.07
    ÑijÑĤ
    0.06
    agit
    0.06
    Activations Density 0.001%

    No Known Activations