© 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. 56237
    Prev
    Next
    INDEX
    Explanations

    duplicate:

    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
    strup
    -0.09
    åIJĥä½ı
    -0.08
    มà¸ĩ
    -0.08
    æł¹æ·±
    -0.08
    åĽĽå¤©
    -0.08
    ecat
    -0.08
    acca
    -0.07
    ë·Ķ
    -0.07
    æĺ¯æĮīçħ§
    -0.07
    riere
    -0.07
    POSITIVE LOGITS
    ãĢĬ
    0.07
     ãĢĬ
    0.07
    æļĤè¡ĮåĬŀæ³ķ
    0.06
     relevant
    0.06
     emot
    0.06
    åŁºçŁ³
    0.06
    åµ
    0.06
    aver
    0.06
    .o
    0.06
    excerpt
    0.06
    Activations Density 0.002%

    No Known Activations