© 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. 28170
    Prev
    Next
    INDEX
    Explanations

    input reading methods

    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
    аÑģÑģа
    -0.07
    iment
    -0.07
    éģµå®ĪåĽ½å®¶
    -0.07
    Ù°
    -0.07
    iac
    -0.07
    à¸Īà¸Ļà¹Į
    -0.06
    åİĨåı²è®°å½ķ
    -0.06
    lets
    -0.06
    ary
    -0.06
    é¡·
    -0.06
    POSITIVE LOGITS
    âĢ¦ãĢį
    0.07
    ä¸ĬåĴĮ
    0.07
    åIJĮæŃ¥
    0.07
    é¼İé¼İ
    0.07
    æĻĵ
    0.07
    weiter
    0.07
    èĩªæ²»åĮº
    0.07
    ä¹ĭæĺŁ
    0.07
    seau
    0.07
    .ut
    0.07
    Activations Density 0.035%

    No Known Activations