© 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. 52085
    Prev
    Next
    INDEX
    Explanations

    rural settings and locations

    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
    ahuan
    -0.08
    ystack
    -0.08
    acon
    -0.08
    ively
    -0.08
    ran
    -0.08
    ltre
    -0.08
    assi
    -0.08
    annis
    -0.08
    ால
    -0.08
    ãĤ£
    -0.08
    POSITIVE LOGITS
    -facing
    0.08
    -mounted
    0.07
    åĴĮåŁİå¸Ĥ
    0.07
    æĽ´ç¾İ好
    0.07
    umat
    0.06
    ÄĻc
    0.06
    ograd
    0.06
    å·¨åıĺ
    0.06
    elling
    0.06
    æ·±å¤Ħ
    0.06
    Activations Density 0.019%

    No Known Activations