© 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. 7903
    Prev
    Next
    INDEX
    Explanations

    drying, dried, dry

    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
    à¤ľà¥įà¤ŀ
    -0.09
    åĴĮåİ¿
    -0.08
    ï¸İ
    -0.08
    akas
    -0.08
    ä¸īé«ĺ
    -0.08
    stuk
    -0.07
    ursion
    -0.07
    ä¿©
    -0.07
    ¾¸
    -0.07
     nhau
    -0.07
    POSITIVE LOGITS
    engel
    0.07
    گاÙĩ
    0.07
    สà¸Ļิà¸Ĺ
    0.07
    idge
    0.07
    ing
    0.07
    ppo
    0.07
    çĥĺå¹²
    0.07
     drying
    0.06
    infeld
    0.06
    åīĤçŃī
    0.06
    Activations Density 0.008%

    No Known Activations