© 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. 55134
    Prev
    Next
    INDEX
    Explanations

    let's see

    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
    ä»°
    -0.07
    äºİ人
    -0.06
    roid
    -0.06
     <!--[
    -0.06
    活水
    -0.06
    apul
    -0.06
     notions
    -0.06
    elon
    -0.06
    ạ
    -0.06
    LY
    -0.06
    POSITIVE LOGITS
    efined
    0.08
    ÏĤ
    0.08
    è¿ĩ好
    0.08
    rán
    0.08
    utenberg
    0.08
    etan
    0.07
    rach
    0.07
    zana
    0.07
    utan
    0.07
    sstr
    0.07
    Activations Density 0.002%

    No Known Activations