© 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. 44539
    Prev
    Next
    INDEX
    Explanations

    alone

    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
    éĩįæĭħ
    -0.07
    çĦ¶åIJİå°Ĩ
    -0.07
    quet
    -0.07
    æ··æĿĤ
    -0.06
    çĦ¶åIJİæĬĬ
    -0.06
    ynu
    -0.06
    éŃĤ
    -0.06
     Nich
    -0.06
    æijĬ
    -0.06
    _inline
    -0.06
    POSITIVE LOGITS
     alone
    0.11
     allein
    0.10
    alone
    0.10
     Alone
    0.10
     seule
    0.09
     seul
    0.09
    ë§Įìľ¼ë¡ľ
    0.09
    ãģłãģijãģ§
    0.09
     solely
    0.09
     seuls
    0.08
    Activations Density 0.063%

    No Known Activations