© 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. 21811
    Prev
    Next
    INDEX
    Explanations

    return value

    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
    à¹Ħมà¹Ī
    -0.12
    à¸ĺรรมà¸Ĭาà¸ķิà¹ģละ
    -0.10
    à¸Ħวาม
    -0.10
    пÑĢоÑĩем
    -0.10
    社ä¼ļ
    -0.10
     nämlich
    -0.10
    à¹Ģà¸Ľà¹ĩà¸Ļ
    -0.09
    åħ´è¶£åĴĮ
    -0.09
    家éķ¿
    -0.09
     edhe
    -0.09
    POSITIVE LOGITS
    /or
    0.39
    /OR
    0.21
    /of
    0.20
    /o
    0.20
    rogen
    0.17
    ÑīеÑĤ
    0.16
    ниÑĨи
    0.16
    rog
    0.16
     sebagainya
    0.16
    erson
    0.15
    Activations Density 1.850%

    No Known Activations