© 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. 38923
    Prev
    Next
    INDEX
    Explanations

    attempt to

    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
    arity
    -0.09
    féle
    -0.08
    /she
    -0.08
    ìį¨
    -0.08
    ething
    -0.08
    /her
    -0.08
    ught
    -0.07
    iding
    -0.07
     essentielles
    -0.07
    Æ°á»Ľng
    -0.07
    POSITIVE LOGITS
    ä½Ĩä¸įéĻIJäºİ
    0.11
    alous
    0.10
    à¸ģารà¸ĵà¹Į
    0.09
    ments
    0.09
    ×Ļ×Ŀ
    0.08
    rans
    0.08
    еÑĢÑĮ
    0.08
    ÑģÑı
    0.07
    cheid
    0.07
    å±ķå¼Ģåħ¨éĥ¨
    0.07
    Activations Density 0.018%

    No Known Activations