© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 21305
    Prev
    Next
    INDEX
    Explanations

    rates, factors, sum, standing, lifetime

    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
    åĽŀäºĭ
    -0.07
    ational
    -0.07
    ptom
    -0.07
    vey
    -0.07
    åı¸ä»¤éĥ¨
    -0.07
    undle
    -0.07
    liable
    -0.07
    好æ±ī
    -0.07
    .pkg
    -0.07
    ãģ¨ãģĵãĤįãģ§ãģĻ
    -0.07
    POSITIVE LOGITS
    è§ģæѤ
    0.08
     thereof
    0.07
     robust
    0.06
    inya
    0.06
    为æѤ
    0.06
    ãģķãģĪ
    0.06
    å°±æѤ
    0.06
    аÑı
    0.06
    èµĦ讯ç½ij
    0.06
    å°±å¾Ī容æĺĵ
    0.06
    Activations Density 0.002%

    No Known Activations