© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 17744
    Prev
    Next
    INDEX
    Explanations

    mathematical and logical problem solving

    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
    _generated
    -0.08
    æ£ł
    -0.08
    kena
    -0.07
    lander
    -0.07
    åºĦéķĩ
    -0.07
    æĸ¹æ³ķæĿ¥
    -0.07
    icch
    -0.07
    ç¼ĵ
    -0.07
    æīįæĺ¯æľĢ
    -0.07
    ä¹Łæľªå¿ħ
    -0.07
    POSITIVE LOGITS
    åıĺ为
    0.12
     becomes
    0.10
    å°±åıĺæĪIJäºĨ
    0.09
     become
    0.09
    åıĺæĪIJ
    0.08
    转åıĺ为
    0.08
    转为
    0.08
     diventa
    0.08
    æĶ¹ä¸º
    0.08
    ister
    0.08
    Activations Density 0.005%

    No Known Activations