© 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. 46082
    Prev
    Next
    INDEX
    Explanations

    numeric expressions with parentheses

    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
    人åĸľæ¬¢
    -0.08
    á»İ
    -0.08
    并请
    -0.07
    lobs
    -0.07
    andia
    -0.07
     Phelps
    -0.07
     pronost
    -0.07
    ihaz
    -0.07
    è§ģçļĦ
    -0.07
    èĶĶ
    -0.07
    POSITIVE LOGITS
    ;y
    0.06
    æĺ¯åħ¶
    0.06
    çIJĨ
    0.06
     simplify
    0.06
    jam
    0.06
    空ä¸Ń
    0.06
    åļ
    0.06
    ä¸ŃæŃ¢
    0.06
    enus
    0.06
    ="--
    0.06
    Activations Density 0.028%

    No Known Activations