© 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. 31497
    Prev
    Next
    INDEX
    Explanations

    B

    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
    æİ¥åıĹ
    -0.08
    åĽºå®ļ
    -0.07
    ungsver
    -0.07
    对è§Ĩ
    -0.06
     capit
    -0.06
     Accept
    -0.06
    解åīĸ
    -0.06
    ic
    -0.06
    å°ģ
    -0.06
    æī¹
    -0.06
    POSITIVE LOGITS
    »
    0.09
    isci
    0.08
    /rfc
    0.08
    æĬĬéĤ£
    0.08
    ึà¸ĩ
    0.08
    gai
    0.08
    ä¸īä¸ĭ乡
    0.07
    !=-
    0.07
    ä¸įèĻļ
    0.07
    RowIndex
    0.07
    Activations Density 0.016%

    No Known Activations