© 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. 20205
    Prev
    Next
    INDEX
    Explanations

    corporate or organizational names

    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
    ä¸Ĭä¸Ģç«ł
    -0.10
    æĻ®äº¬
    -0.09
    çĴŁ
    -0.09
     billions
    -0.09
    odesk
    -0.09
     ``(
    -0.09
    ä¹łæĢ»ä¹¦è®°
    -0.09
    æѦèѦ
    -0.09
    ForEach
    -0.09
    æ¬§çĽŁ
    -0.09
    POSITIVE LOGITS
    å½ĵæŶ
    0.12
    å½ĵæŶçļĦ
    0.11
    åľ¨å½ĵæŶ
    0.09
    çķ¶æĻĤ
    0.09
     unidentified
    0.08
     damals
    0.08
     (?)
    0.08
     unnamed
    0.08
    0.08
    æŶ任
    0.07
    Activations Density 1.074%

    No Known Activations