© 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. 23487
    Prev
    Next
    INDEX
    Explanations

    invention relates or consists

    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
    asa
    -0.07
     zev
    -0.07
    _FIND
    -0.07
    editable
    -0.07
    ä¹
    -0.07
    åħ¨ä½ĵå¸ĪçĶŁ
    -0.07
     mystery
    -0.07
    å¦Ĥæŀľåı¯ä»¥
    -0.07
    ä¸įå¦Ĥ
    -0.07
    ä¸ĢåĪĩ
    -0.07
    POSITIVE LOGITS
    æīįèĥ½ä¿Ŀè¯ģ
    0.08
    åIJ¦åĪĻ
    0.08
    为ä»Ģä¹Īåij¢
    0.07
    åIJ¦åĪĻä¼ļ
    0.07
     Otherwise
    0.07
    çĭ¬æľī
    0.07
    ä¸įçĦ¶
    0.06
    ondi
    0.06
    _super
    0.06
    Otherwise
    0.06
    Activations Density 0.254%

    No Known Activations