© 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. 21948
    Prev
    Next
    INDEX
    Explanations

    admission, shock, type, phosphate, response, group

    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
    è¿Ļä¹Īå¤ļçļĦ
    -0.06
    ä¸į为
    -0.06
    ×IJ×ķת
    -0.06
    å¸Į
    -0.06
    à¤ľà¥Ģ
    -0.06
    äºĽä»Ģä¹Ī
    -0.06
    æĹ¢
    -0.06
    çļĦè¿ĺæľī
    -0.06
    gan
    -0.06
     Ñģме
    -0.06
    POSITIVE LOGITS
    åĴĮ第äºĮ
    0.08
    enburg
    0.08
    ADED
    0.08
    nél
    0.07
    ç½Ĺå¾·
    0.07
    ä¸Ĭ交
    0.07
    åĴĮ第
    0.07
     ($.
    0.07
    idor
    0.07
    对大家
    0.07
    Activations Density 0.084%

    No Known Activations