© 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. 48040
    Prev
    Next
    INDEX
    Explanations

    numbers and dates

    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
    èIJ½æĹ¥
    -0.07
    ä»»ä½ķä¸Ģç§į
    -0.06
    ingo
    -0.06
    è·ijåĪ°
    -0.06
    çĶ¨çĶµ
    -0.06
    å°½æĥħåľ°
    -0.06
    æľīæĸ°çļĦ
    -0.06
    ogie
    -0.06
    好å¿ĥæĥħ
    -0.06
    å±±é«ĺ
    -0.06
    POSITIVE LOGITS
    å§ĭ
    0.10
    elib
    0.08
    èĥģ
    0.08
     BuzzFeed
    0.08
    Ä«b
    0.08
    awali
    0.08
    ثة
    0.07
    åŁºæķ°
    0.07
     prek
    0.07
     ÐĺзÑĥ
    0.07
    Activations Density 0.056%

    No Known Activations