© 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. 7414
    Prev
    Next
    INDEX
    Explanations

    being a part of

    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
     likely
    -0.10
    å¤Ł
    -0.07
    likely
    -0.07
     importantly
    -0.07
    å¿ħ
    -0.06
    ä¸įåı¯èĥ½
    -0.06
    å¾ĪæľīæĦıæĢĿ
    -0.06
    æĦŁäºº
    -0.06
     Likely
    -0.06
    å¾Īæ·±
    -0.06
    POSITIVE LOGITS
    åĽłä¸ºè¿Ļ
    0.12
    å°¤åħ¶æĺ¯
    0.11
    å°¤åħ¶
    0.10
     Especially
    0.10
     especially
    0.09
    å°¤åħ¶æĺ¯åľ¨
    0.09
    especially
    0.09
    çī¹åĪ«æĺ¯
    0.09
    åĵªæĢķ
    0.09
     zwÅĤaszcza
    0.09
    Activations Density 0.889%

    No Known Activations