© 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. 56413
    Prev
    Next
    INDEX
    Explanations

    `/problems`

    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
    çļĦä»»ä½ķ
    -0.07
    å¹ħ
    -0.07
    并ç»ı
    -0.07
    æĺ¯æľ¬
    -0.07
    azy
    -0.07
    è¿ĩç¥ŀ
    -0.07
    NodeType
    -0.06
    åıĬåIJĦ
    -0.06
    çĻ½äºĨ
    -0.06
    AdapterFactory
    -0.06
    POSITIVE LOGITS
    æ¶īåıĬåĪ°
    0.08
    çݩ转
    0.07
    éĤ£éģĵ
    0.07
    resti
    0.07
    æĬķèµĦé¡¹çĽ®
    0.07
    ubr
    0.07
    解åĨ³
    0.07
    .detect
    0.07
     Challenge
    0.07
     involving
    0.07
    Activations Density 0.175%

    No Known Activations