© 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. 44764
    Prev
    Next
    INDEX
    Explanations

    download / followed by text

    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
    ixon
    -0.07
    åĪ«ç¦»
    -0.07
    ä¸Ģè¿ŀ
    -0.07
    ilder
    -0.07
    转载请注æĺİåĩºå¤Ħ
    -0.06
    erta
    -0.06
    ager
    -0.06
    çĥŃéŨçļĦ
    -0.06
    acro
    -0.06
    ãģįãĤĥ
    -0.06
    POSITIVE LOGITS
    illes
    0.07
    说åĪ°è¿ĻéĩĮ
    0.07
    vron
    0.07
    rophy
    0.07
    溯
    0.07
    ä¸İä½ľçĶ¨
    0.07
    oppi
    0.07
    siz
    0.06
    ÐķÐĿÐĿÐŀ
    0.06
    å©Ĩ
    0.06
    Activations Density 0.009%

    No Known Activations