© 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. 16034
    Prev
    Next
    INDEX
    Explanations

    considering or lists

    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
    åĺĽ
    -0.08
    éĢļè¿ĩ使çĶ¨
    -0.08
    è¿Ļä¸ĢçĤ¹
    -0.07
    åıªå¥½
    -0.07
    RID
    -0.07
    à¸Ļัà¹Īà¸Ļà¹Ģà¸Ńà¸ĩ
    -0.07
    æĺ¯åĶ¯ä¸Ģ
    -0.07
    ocale
    -0.07
    éĢļè¿ĩå°Ĩ
    -0.07
    çļĦä¸Ģç§įæĸ¹å¼ı
    -0.07
    POSITIVE LOGITS
     altrett
    0.09
     lesquelles
    0.08
    åĪĨåĪ«æĺ¯
    0.08
     à¹Ħà¸Ķà¹īà¹ģà¸ģà¹Ī
    0.08
    nerg
    0.07
     lesquels
    0.07
    åĮħæĭ¬ä½Ĩä¸įéĻIJäºİ
    0.07
    bes
    0.07
    åĪĨåĪ¥æĺ¯
    0.06
    icana
    0.06
    Activations Density 0.397%

    No Known Activations