© 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. 23146
    Prev
    Next
    INDEX
    Explanations

    mentioning

    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
    ä»ĸ表示
    -0.09
    她表示
    -0.08
     ÐĴÑģÑĤÑĢе
    -0.08
    minster
    -0.08
    ccion
    -0.08
    schlä
    -0.08
    à¹īว
    -0.08
    endale
    -0.08
    olumbia
    -0.08
    IMUM
    -0.08
    POSITIVE LOGITS
    ä½Ĩä¸įéĻIJäºİ
    0.10
     nhợ
    0.07
    Ñħодом
    0.07
    æ¦Ķ
    0.07
    ifest
    0.07
    æī«åľ°
    0.07
    ãģ¹ãģį
    0.07
    为æŃ¢
    0.07
    er
    0.07
    orr
    0.07
    Activations Density 0.015%

    No Known Activations