© 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. 7742
    Prev
    Next
    INDEX
    Explanations

    .yml files

    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
    åĪ«
    -0.08
    æĭ¬
    -0.08
    ugel
    -0.08
    ares
    -0.07
    è°Ĵ
    -0.07
    ä¸ĩæĪ·
    -0.07
    esign
    -0.07
    ä¸ĩéĩĮ
    -0.07
    erstand
    -0.07
    fyl
    -0.07
    POSITIVE LOGITS
    åĿ¦
    0.07
     thereof
    0.07
    çī
    0.07
     Nack
    0.06
    olas
    0.06
    amped
    0.06
     Weiner
    0.06
    ç¾İä¸Ń
    0.06
    els
    0.06
    æĹłéĿŀ
    0.06
    Activations Density 0.179%

    No Known Activations