© 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. 4861
    Prev
    Next
    INDEX
    Explanations

    particular, particularly

    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
    sti
    -0.07
    agt
    -0.07
    alp
    -0.06
    raš
    -0.06
    queta
    -0.06
    å°±åĽłä¸º
    -0.06
    mio
    -0.06
     KEP
    -0.06
    ritel
    -0.06
    zer
    -0.06
    POSITIVE LOGITS
    è¿ĺåĮħæĭ¬
    0.11
    éĩįçĤ¹æĺ¯
    0.09
    å®ĥè¿ĺ
    0.08
    缮çļĦæĺ¯
    0.08
    owie
    0.08
    å½¼ãģ¯
    0.08
    çĿĢçľ¼äºİ
    0.08
     it
    0.08
    åºĶåĮħæĭ¬
    0.08
    æ¶īåıĬåĪ°
    0.08
    Activations Density 0.395%

    No Known Activations