© 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. 1255
    Prev
    Next
    INDEX
    Explanations

    prime factors, descending order, punctuation

    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
    åĽ½æľį
    -0.07
    åĽłä¸ºè¿ĻäºĽ
    -0.07
    äº
    -0.07
    çº¿åĽ¾
    -0.06
    äºĭåħĪ
    -0.06
    -bs
    -0.06
    .pol
    -0.06
    æĴijèµ·
    -0.06
    loo
    -0.06
    imedia
    -0.06
    POSITIVE LOGITS
    ýt
    0.07
    pun
    0.07
    alak
    0.07
    rosse
    0.07
    夫æĸ¯åŁº
    0.06
    elda
    0.06
    æİĥ
    0.06
    å±ĪæĮĩ
    0.06
    aji
    0.06
    URI
    0.06
    Activations Density 0.001%

    No Known Activations