© 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. 26562
    Prev
    Next
    INDEX
    Explanations

    replacereplacingreplacement

    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
    çĭ¬ç«ĭ
    -0.08
     izol
    -0.08
     separ
    -0.07
    anski
    -0.07
    åѤç«ĭ
    -0.07
     alá
    -0.07
    rico
    -0.07
    åı·åı¬
    -0.07
     isol
    -0.07
    anie
    -0.07
    POSITIVE LOGITS
    æĽ¿æį¢
    0.17
    replace
    0.15
     replace
    0.14
    ç½®æį¢
    0.13
     replaces
    0.13
     replacing
    0.13
    .replace
    0.13
     Replace
    0.13
    åıĸ代
    0.12
     replacement
    0.12
    Activations Density 0.100%

    No Known Activations