© 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. 21183
    Prev
    Next
    INDEX
    Explanations

    Spark and JavaFX code

    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
    æłĢåŃIJ
    -0.08
    çĪĨ竹
    -0.08
     Israelis
    -0.08
    owitz
    -0.08
    ufe
    -0.08
    çIJ²
    -0.07
    atham
    -0.07
     Israeli
    -0.07
    ukse
    -0.07
     lá»ĩ
    -0.07
    POSITIVE LOGITS
     Uzbek
    0.08
    æľ±åħĥçĴĭ
    0.07
    åħĥ代
    0.07
    .scala
    0.07
     mac
    0.07
     Welsh
    0.07
    æ¸Ń
    0.07
     Cerv
    0.07
    åĪĺéĤ¦
    0.06
     Spokane
    0.06
    Activations Density 0.124%

    No Known Activations