© 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. 58522
    Prev
    Next
    INDEX
    Explanations

    string and array manipulation

    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
    kking
    -0.08
     поÑģÑĤанов
    -0.07
    ensif
    -0.07
    ãĥ«ãĥ¼
    -0.07
    SqlCommand
    -0.07
     corrida
    -0.07
    .offsetWidth
    -0.07
     Kraj
    -0.07
    getResource
    -0.07
    uas
    -0.07
    POSITIVE LOGITS
    àºŃàºĩ
    0.06
    typed
    0.06
    çļĦèĤ¡æĿĥ
    0.06
    onga
    0.06
    .removeEventListener
    0.06
     ch
    0.06
    ä¸įç»ı
    0.06
     repres
    0.06
    еÑģÑĤо
    0.06
    sw
    0.05
    Activations Density 0.012%

    No Known Activations