© 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. 44226
    Prev
    Next
    INDEX
    Explanations

    mathematical or technical concepts

    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
    pps
    -0.08
    vs
    -0.07
    ä¹ĭæģĭ
    -0.07
    ook
    -0.07
    amor
    -0.07
    认åĩĨ
    -0.07
    åĬ³åĬ¡
    -0.07
    VS
    -0.07
    qs
    -0.06
    aly
    -0.06
    POSITIVE LOGITS
    inete
    0.08
    çľĭä¼¼
    0.08
    iners
    0.08
    ifr
    0.07
    utu
    0.07
    engi
    0.07
     erek
    0.07
    inata
    0.06
    çī¹åĭĴ
    0.06
    achsen
    0.06
    Activations Density 0.031%

    No Known Activations