© 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. 33397
    Prev
    Next
    INDEX
    Explanations

    although

    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
    åĪ»éª¨éĵŃ
    -0.09
    ÄĽn
    -0.09
    emers
    -0.08
    大ä¸ĵåıĬ以ä¸ĬåѦåİĨ
    -0.08
    å®Įæķ´çīĪ
    -0.08
    缴è§ĤçļĦæĸ¹å¼ı
    -0.07
    æĬĬåŃ¦ä¹ł
    -0.07
    å°±æĢķ
    -0.07
    åĢ¼å¾Ĺä¹°
    -0.07
    oner
    -0.07
    POSITIVE LOGITS
     moj
    0.07
    (!
    0.07
    人ä¸į
    0.07
     vo
    0.07
    å½ĵçĦ¶æĺ¯
    0.06
     her
    0.06
    ngth
    0.06
    ä¾Ŀæ³ķ
    0.06
     باÙĦطبع
    0.06
     кÑģÑĤаÑĤи
    0.06
    Activations Density 0.992%

    No Known Activations