© 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. 11055
    Prev
    Next
    INDEX
    Explanations

    N/A placeholders

    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
    vestment
    -0.07
    æħ§èģª
    -0.07
    anyi
    -0.07
    {}",
    -0.07
    {}".
    -0.06
    vio
    -0.06
    à¹īวà¸Ļ
    -0.06
    产åĵģçļĦè´¨éĩı
    -0.06
    ]+)/
    -0.06
    arka
    -0.06
    POSITIVE LOGITS
    çĤ¬
    0.07
    ä¸įéĩįè¦ģ
    0.07
    osit
    0.07
    å¸Ĥ
    0.06
     Grove
    0.06
    ä¸Ĭèħº
    0.06
    elj
    0.06
    asar
    0.06
    inery
    0.06
    asel
    0.06
    Activations Density 0.018%

    No Known Activations