© 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. 744
    Prev
    Next
    INDEX
    Explanations

    pay etc

    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
    ead
    -0.08
    ardin
    -0.08
    ä¸īäºĶ
    -0.07
    ä¸īéĩĮ
    -0.07
    uter
    -0.07
    _eng
    -0.07
    é¹ĥ
    -0.07
    ëĤł
    -0.07
    ullet
    -0.07
    _called
    -0.07
    POSITIVE LOGITS
    prog
    0.07
    åħ·ä½ĵéĹ®é¢ĺ
    0.07
    交éĶĻ
    0.07
    æķ´ä½ĵä¸Ĭ
    0.07
    åıĺçļĦ
    0.07
    apore
    0.07
     Pedi
    0.06
    管åĪ¶
    0.06
    apar
    0.06
    yka
    0.06
    Activations Density 0.012%

    No Known Activations