© 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. 39739
    Prev
    Next
    INDEX
    Explanations

    suggesting alternatives or fixes

    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
    Tra
    -0.07
    ogos
    -0.07
    åĹħ
    -0.06
    tra
    -0.06
    轨迹
    -0.06
    äºĨä¸ĢçĤ¹
    -0.06
    undan
    -0.06
    æľīä¸ĢçĤ¹
    -0.06
    ä¸Ń度
    -0.06
    éł
    -0.06
    POSITIVE LOGITS
    instead
    0.12
    èĢĮä¸įæĺ¯
    0.12
     instead
    0.11
    è¿Ļæīįæĺ¯
    0.10
    rather
    0.09
     Instead
    0.09
    æŃ£è§ĦçļĦ
    0.09
    æŃ£è§Ħ
    0.09
    Instead
    0.09
    羣æŃ£
    0.09
    Activations Density 0.142%

    No Known Activations