© 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. 61778
    Prev
    Next
    INDEX
    Explanations

    followed by common continuations

    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
    åĽłä¸ºä½ł
    -0.11
    åĽłä¸ºæĪij
    -0.10
    åĽłä¸ºæĪij们
    -0.10
    æīĢ以æīį
    -0.10
    è¿Ļæĺ¯åĽłä¸º
    -0.10
    ä»İèĢĮ使
    -0.10
    åĽłä¸ºå¥¹
    -0.10
    åĽłä¸ºåľ¨
    -0.10
    åĽłä¸ºåħ¶
    -0.09
    åį´åĽłä¸º
    -0.09
    POSITIVE LOGITS
    ä¹Łå°±ä¸į
    0.08
     Ñģмело
    0.08
    oud
    0.08
    éĹ®é¢ĺæĿ¥äºĨ
    0.07
    å²Ĥä¸įæĺ¯
    0.07
    ừa
    0.07
    illy
    0.07
    å°±æľīäºĨ
    0.07
    åľ¨è¿Ļæĸ¹éĿ¢
    0.07
    ä¸į误
    0.07
    Activations Density 0.451%

    No Known Activations