© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 60185
    Prev
    Next
    INDEX
    Explanations

    JetBrains s.r.o

    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
    æ²ī
    -0.09
    utura
    -0.08
    opia
    -0.07
    adera
    -0.07
    วล
    -0.07
    มูล
    -0.07
    审计
    -0.07
    quete
    -0.07
     Hosp
    -0.07
    åŁºéĩijçļĦ
    -0.07
    POSITIVE LOGITS
    æĽĻ
    0.07
     $$$
    0.07
    æĤ²æ¬¢
    0.06
    身为
    0.06
    人ä¸ĸ
    0.06
    eberg
    0.06
     hear
    0.06
     perfe
    0.06
    ãĥŃãĤ·ãĤ¢
    0.06
    ences
    0.06
    Activations Density 0.005%

    No Known Activations