© 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. 39502
    Prev
    Next
    INDEX
    Explanations

    is followed by an article or noun

    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
    à¹īà¸ĩ
    -0.07
    issa
    -0.07
     pros
    -0.07
     ÑĦакÑĤÑĥ
    -0.07
    usercontent
    -0.06
    terer
    -0.06
     hela
    -0.06
    _SIM
    -0.06
    icia
    -0.06
    çĥĽåħī
    -0.06
    POSITIVE LOGITS
    ERT
    0.08
     trình
    0.07
    奴
    0.07
    mam
    0.07
    nard
    0.07
    own
    0.07
     getIndex
    0.07
    æįº
    0.07
    enden
    0.06
    _editor
    0.06
    Activations Density 0.005%

    No Known Activations