© 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. 10665
    Prev
    Next
    INDEX
    Explanations

    together

    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
    ़
    -0.11
    ation
    -0.10
    并èĮĤ
    -0.10
    -0.09
    erweise
    -0.09
    noinspection
    -0.09
    大åı¯
    -0.09
    itory
    -0.09
    åĽŀæĹıèĩªæ²»åĮº
    -0.09
    à¸ģารà¸Ĺำà¸ĩาà¸Ļ
    -0.09
    POSITIVE LOGITS
    -sama
    0.15
    ings
    0.11
    hips
    0.08
    isons
    0.07
    prises
    0.07
    NESS
    0.07
    Ĥ
    0.06
    INGS
    0.06
    anea
    0.06
    lijk
    0.06
    Activations Density 0.029%

    No Known Activations