© 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. 10756
    Prev
    Next
    INDEX
    Explanations

    defining variables or methods

    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
    èĢĮä¸Ķè¿ĺæľī
    -0.06
    ç»ĻçĶ¨æĪ·
    -0.06
    (((
    -0.06
    é¥Ń
    -0.06
    åIJİåį³åı¯
    -0.06
    ÙĪدة
    -0.06
    elda
    -0.06
    äºİæĺ¯å°±
    -0.06
    èĢĮä¸Ķè¿ĺæĺ¯
    -0.06
    verbose
    -0.06
    POSITIVE LOGITS
    OrCreate
    0.08
    "./
    0.08
     serialVersionUID
    0.07
     VÅ©ng
    0.07
     _$
    0.07
    Ñĥл
    0.07
    -decoration
    0.07
    ampler
    0.07
    éĽ
    0.07
    足ä¸įåĩºæĪ·
    0.07
    Activations Density 0.021%

    No Known Activations