© 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. 41239
    Prev
    Next
    INDEX
    Explanations

    but also

    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
    人ä¸į
    -0.09
    eme
    -0.08
    ÏģηÏĤ
    -0.07
    egasus
    -0.07
    ices
    -0.07
    resco
    -0.07
    мож
    -0.07
    huri
    -0.06
    尽管å¦ĤæѤ
    -0.06
    eras
    -0.06
    POSITIVE LOGITS
    æł©
    0.08
    λει
    0.07
    è¿ĺæľīçĿĢ
    0.07
     mercad
    0.07
    deren
    0.07
    AndGet
    0.07
     ÙĢÙĢ
    0.07
    à¸ģà¹ĩà¸ķาม
    0.07
     sondern
    0.06
    éĤĦæĺ¯è¦ģ
    0.06
    Activations Density 0.033%

    No Known Activations