© 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. 50279
    Prev
    Next
    INDEX
    Explanations

    before and after

    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
    кÑĨии
    -0.09
    èijĨ
    -0.09
    è¿ĩç¨ĭå½ĵä¸Ń
    -0.08
    éĻ¸
    -0.07
    rauch
    -0.07
    æĥļ
    -0.07
    ongo
    -0.07
     Kudus
    -0.07
    åİĨç¨ĭ
    -0.07
    éĻĨ
    -0.07
    POSITIVE LOGITS
    ç¿
    0.07
    水泡
    0.07
    halb
    0.06
     Ñģва
    0.06
    è¶ħè¶Ĭ
    0.06
    iders
    0.06
    neath
    0.06
    wipe
    0.06
     Cros
    0.06
    ä¸ĸçķĮ第ä¸Ģ
    0.06
    Activations Density 0.222%

    No Known Activations