© 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. 49327
    Prev
    Next
    INDEX
    Explanations

    -4

    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
     Mois
    -0.07
    anto
    -0.07
    omor
    -0.07
    çĽ¸ä¼¼æĸĩçĮ®
    -0.07
    stech
    -0.06
    sWith
    -0.06
    ogh
    -0.06
    çĹº
    -0.06
    itals
    -0.06
    çİ
    -0.06
    POSITIVE LOGITS
    kke
    0.07
    åĬ©
    0.07
     eset
    0.06
    idente
    0.06
    <|box_end|>
    0.06
    inkin
    0.06
    eli
    0.06
    liy
    0.06
    unic
    0.06
    elin
    0.06
    Activations Density 0.147%

    No Known Activations