© 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. 7747
    Prev
    Next
    INDEX
    Explanations

    mathematical equations and code

    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
    顺å¿ĥ
    -0.08
    è§Ħå®ļçļĦåħ¶ä»ĸ
    -0.08
    ä»»ä½ķ责任
    -0.08
    icode
    -0.08
    Ùħاس
    -0.08
    ë°
    -0.08
    ared
    -0.08
    zten
    -0.07
    æĺ¯çľŁ
    -0.07
     Blades
    -0.07
    POSITIVE LOGITS
     imp
    0.06
    çĶŁæ´»
    0.06
    gars
    0.06
    æĪijåij¢
    0.06
    人æµģ
    0.06
    atil
    0.06
     pret
    0.06
    æ·»
    0.06
    eley
    0.06
     Pur
    0.06
    Activations Density 0.015%

    No Known Activations