© 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. 1192
    Prev
    Next
    INDEX
    Explanations

    coding concepts and ideas

    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
    æ½
    -0.08
    Ä©a
    -0.08
    illis
    -0.08
    ανε
    -0.07
    çĶŁæºIJ
    -0.07
    éĨ¤
    -0.07
    akup
    -0.07
    arka
    -0.07
    ibold
    -0.07
     Zav
    -0.07
    POSITIVE LOGITS
    rome
    0.07
     meta
    0.07
    meta
    0.07
    ç¯ĩ
    0.07
    æĬ½
    0.07
    äj
    0.06
    док
    0.06
     META
    0.06
    META
    0.06
    åĤ¬
    0.06
    Activations Density 0.934%

    No Known Activations