© 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. 60098
    Prev
    Next
    INDEX
    Explanations

    drills, current, gyros, parallels

    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
    Not in Any Lists

    No Comments

    Negative Logits
    åĸľè¿İ
    -0.09
    æĥ³æĸ¹
    -0.09
     ÑģÑĤаÑĤÑĥÑģ
    -0.08
     scripted
    -0.08
    罪éŃģ祸é¦ĸ
    -0.08
    檸
    -0.08
     Duarte
    -0.08
    μαÏĦο
    -0.08
    Reuse
    -0.08
    ä¸Ģä¼Ĺ
    -0.08
    POSITIVE LOGITS
     (§
    0.08
    chief
    0.07
     prostitutes
    0.07
     ordin
    0.07
    immen
    0.07
    å¾®åķĨ
    0.07
     chief
    0.07
     erect
    0.07
     §§
    0.07
     §
    0.07
    Activations Density 0.022%

    No Known Activations