© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 51703
    Prev
    Next
    INDEX
    Explanations

    hotel, here, came, custom, lean, hiking, diary, mainstream, State, award

    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
     impactful
    -0.08
    äºĨçīĩåĪ»
    -0.08
    åįĬæŃ¥
    -0.07
    umente
    -0.07
    ä¸Ĭä¸Ģç«ł
    -0.07
    ourced
    -0.07
    æĹ¥æ¶Īæģ¯
    -0.07
    ÏĥÏĦή
    -0.07
    æīĵéĢłæĪIJ为
    -0.07
    aa
    -0.07
    POSITIVE LOGITS
     (âĢ¦)
    0.09
     ___
    0.08
     [âĢ¦]
    0.07
    åľ¨è¿ĻåĦ¿
    0.07
     someday
    0.07
    ä¸ĢçĤ¹åĦ¿
    0.07
    æľīçĤ¹åĦ¿
    0.07
     ________
    0.07
     ______
    0.07
     aggrav
    0.07
    Activations Density 0.165%

    No Known Activations