© 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. 27743
    Prev
    Next
    INDEX
    Explanations

    normal, pdf, observations

    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
    æ´»
    -0.08
     pregn
    -0.07
    å¢ŀ产
    -0.07
    寺
    -0.07
    è´Łè´£ä»»
    -0.06
    éĤĤ
    -0.06
     tighter
    -0.06
     recom
    -0.06
    ảo
    -0.06
     reefs
    -0.06
    POSITIVE LOGITS
    æĹłéĹ»
    0.08
     pdf
    0.08
    æľįä»İ
    0.07
     contamin
    0.07
     Uniform
    0.07
    ikli
    0.07
    åģľæľº
    0.07
    èĮµ
    0.07
    çľŁå¥½
    0.07
    -pdf
    0.06
    Activations Density 0.007%

    No Known Activations