© 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. 4760
    Prev
    Next
    INDEX
    Explanations

    punctuation and connecting words

    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
    éĢļ常æĺ¯
    -0.06
    ä¹Łéĥ½æĺ¯
    -0.06
    renz
    -0.06
     later
    -0.06
    ä»ķ
    -0.06
    prefer
    -0.06
    åł
    -0.06
    ä¹Łä¸İ
    -0.06
     equip
    -0.06
    ä¹Łä½¿å¾Ĺ
    -0.06
    POSITIVE LOGITS
    ä¹Łä¸įä¾ĭå¤ĸ
    0.12
    亦çĦ¶
    0.09
     accordingly
    0.08
    åľ¨è¿Ļæĸ¹éĿ¢
    0.08
    strom
    0.08
    etat
    0.07
    esters
    0.07
    kamer
    0.07
    STYPE
    0.07
     Dân
    0.07
    Activations Density 0.055%

    No Known Activations