© 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. 43101
    Prev
    Next
    INDEX
    Explanations

    used for example within

    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
    ä¸įåıĬ
    -0.08
     -:
    -0.08
    infra
    -0.08
    onnal
    -0.08
     Universo
    -0.08
    ÙĨاÙĨ
    -0.08
    ünst
    -0.08
    esp
    -0.08
    详æĥħ请
    -0.08
    probably
    -0.08
    POSITIVE LOGITS
     beispielsweise
    0.08
    尤为
    0.07
    ä¾ĭå¦Ĥ
    0.07
    æĽ´éĩįè¦ģçļĦæĺ¯
    0.07
    æŃ£æĺ¯åľ¨
    0.06
    -
    0.06
    åħħè£ķ
    0.06
     напÑĢимеÑĢ
    0.06
    æĹłæļĩ
    0.06
    尤为éĩįè¦ģ
    0.06
    Activations Density 0.001%

    No Known Activations