© 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. 16059
    Prev
    Next
    INDEX
    Explanations

    yet, still, also, simultaneously

    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
     zwar
    -0.11
     although
    -0.11
    èĻ½çĦ¶
    -0.10
    ä¸įä»ħåľ¨
    -0.10
    èĻ½çĦ¶æľī
    -0.09
    ä¸įä½Ĩ
    -0.09
    èĻ½çĦ¶åľ¨
    -0.09
    ä¸įä»ħ
    -0.09
    èĻ½çĦ¶æ²¡æľī
    -0.09
    although
    -0.09
    POSITIVE LOGITS
    ä¸įèĩ³äºİ
    0.09
     zároveÅĪ
    0.09
    åıĪä¸į失
    0.09
    ä¸įä¹ı
    0.09
    åıĪèĥ½
    0.09
    åıĪä¸įæĺ¯
    0.08
    ä¹ŁæľīäºĽ
    0.08
    ä¸įå¾Ĺä¸į说
    0.08
    erenc
    0.08
    åį´æľī
    0.08
    Activations Density 0.151%

    No Known Activations