© 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. 45889
    Prev
    Next
    INDEX
    Explanations

    re-binarization, normalized, or converted

    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
     ÑĢÑĥбе
    -0.08
    .watch
    -0.08
    æĮģä¹ĭ以
    -0.07
    ä½ĨéļıçĿĢ
    -0.07
    ä¹ĭå¤ļ
    -0.07
     terce
    -0.07
    å¤ļäºİ
    -0.07
    è¶Ĭå¤ļ
    -0.07
    ovable
    -0.07
    ä¸į移
    -0.07
    POSITIVE LOGITS
    绣ä¸Ģ
    0.08
    绣ä¸ĢçļĦ
    0.08
    /remove
    0.08
    æ¶ĪéĻ¤äºĨ
    0.08
    使åħ¶
    0.08
     Flatten
    0.08
    æ¶ĪéĻ¤
    0.08
    åħįå¾Ĺ
    0.08
     eliminate
    0.07
     converts
    0.07
    Activations Density 0.087%

    No Known Activations