© 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. 28108
    Prev
    Next
    INDEX
    Explanations

    numbers and special characters

    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
    éĿŀåħ¬
    -0.08
    astr
    -0.08
    adeira
    -0.08
    åįĬè¾¹
    -0.08
    ä¸ĩåĽ½
    -0.08
    大åħ¸
    -0.08
    ataka
    -0.08
    iaÅĤa
    -0.08
    ingers
    -0.08
    ÏĢει
    -0.08
    POSITIVE LOGITS
    sv
    0.07
    à¸ļล
    0.07
    转åĮĸæĪIJ
    0.06
     deci
    0.06
    adu
    0.06
    转åĮĸ为
    0.06
    ont
    0.06
    pon
    0.06
    ã
    0.06
    ees
    0.06
    Activations Density 0.001%

    No Known Activations