© 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. 44368
    Prev
    Next
    INDEX
    Explanations

    offering free cash or gift card

    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
    oty
    -0.07
    inkel
    -0.07
    íĦ´
    -0.07
    çļĦåĪĨ
    -0.07
    çIJĨ
    -0.07
    pth
    -0.07
    retval
    -0.07
    reme
    -0.07
    pname
    -0.06
    hopefully
    -0.06
    POSITIVE LOGITS
    wen
    0.08
    å¾Ģå¾Ģæĺ¯
    0.07
     often
    0.07
    acro
    0.07
    acre
    0.07
     Often
    0.07
    å°±æĽ¾
    0.07
    acia
    0.07
    acr
    0.07
    oston
    0.07
    Activations Density 0.029%

    No Known Activations