© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 34907
    Prev
    Next
    INDEX
    Explanations

    incubated, collected, evaluated, washed, diluted, incubated, catheter, available, ventilated, fabricated, inoculated

    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
    Negative Logits
     certos
    -0.11
     certas
    -0.11
    ä¸įäºĨå¤ļä¹ħ
    -0.09
    åĴ±ä»¬çļĦ
    -0.09
    éĤ£ä¹Īå¤ļ
    -0.08
     ciertos
    -0.08
    åĥıä½ł
    -0.08
    æŁIJäºĽ
    -0.08
    .club
    -0.08
     certe
    -0.08
    POSITIVE LOGITS
     consisted
    0.08
    å½ĵæŶ
    0.07
    为确ä¿Ŀ
    0.07
     invariably
    0.07
     reportedly
    0.07
     firstly
    0.07
     ensuing
    0.07
    åľ¨å½ĵæŶ
    0.07
    each
    0.07
    æ¯ı天
    0.06
    Activations Density 0.640%

    No Known Activations