© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 48359
    Prev
    Next
    INDEX
    Explanations

    need assistance or am trying

    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
    ivas
    -0.07
    ie
    -0.07
    ä¸Ģ声
    -0.07
    udas
    -0.06
    åĮĸåĴĮ
    -0.06
    ↵
    -0.06
    rish
    -0.06
     recruiter
    -0.06
     seamlessly
    -0.06
    ä»Ĺ
    -0.06
    POSITIVE LOGITS
    ACS
    0.08
    oken
    0.07
    磶
    0.07
    âĸ·
    0.07
    ház
    0.07
    æĽ¦
    0.07
    $body
    0.07
    dv
    0.07
    SearchParams
    0.07
    å¤ĸç§ijæīĭæľ¯
    0.07
    Activations Density 0.001%

    No Known Activations