© 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. 58979
    Prev
    Next
    INDEX
    Explanations

    punctuation or symbols

    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
    <|fim_prefix|>
    -0.07
    geries
    -0.07
    życz
    -0.06
    lik
    -0.06
    Äıte
    -0.06
    åħīå½±
    -0.06
    ÅĽni
    -0.06
    æĥ¹
    -0.06
     Liter
    -0.06
    便æľī
    -0.05
    POSITIVE LOGITS
    å§Ĺ
    0.09
    âĺħâĺħ
    0.08
    æ¦Ī
    0.08
    зÑĮ
    0.08
    chet
    0.07
    بÙĬب
    0.07
    orna
    0.07
    å¦Ĥèį¼
    0.07
    çİĭæ°¸
    0.07
    çĤ¹å¼Ģ
    0.07
    Activations Density 4.563%

    No Known Activations