© 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. 8987
    Prev
    Next
    INDEX
    Explanations

    fraction of 1

    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
    ī
    -0.07
    itra
    -0.07
    ingang
    -0.07
    à¸ĺาร
    -0.06
    жан
    -0.06
    åĨ·èIJ½
    -0.06
    inga
    -0.06
    elang
    -0.06
    ETO
    -0.06
    ÏģαÏĥ
    -0.06
    POSITIVE LOGITS
    pecially
    0.08
    buquerque
    0.08
    åĶij
    0.08
    æŀģäºĨ
    0.07
    gesch
    0.07
    áva
    0.07
    ihaz
    0.07
    _DECLARE
    0.07
    edom
    0.07
    ÙħÙĪÙĦ
    0.07
    Activations Density 0.003%

    No Known Activations