© 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. 30970
    Prev
    Next
    INDEX
    Explanations

    electrons, water, steam, Internet, paper

    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
    ÅĽl
    -0.07
    å±ħçĦ¶
    -0.07
    adoo
    -0.07
    ãĤħãģĨ
    -0.06
    ÑĢани
    -0.06
    蹦蹦
    -0.06
     Barbar
    -0.06
    ölt
    -0.06
     кое
    -0.06
    sver
    -0.06
    POSITIVE LOGITS
    æĪĸåħ¶ä»ĸ
    0.10
    éĶĻ误æĪĸ
    0.09
    æĪĸåħ¶å®ĥ
    0.09
    æĬķèµĦæĪĸ
    0.09
    ãģłãģ£ãģŁãĤĬ
    0.09
    ä¹ĭäºİ
    0.08
    为ä¾ĭ
    0.08
    人æĪĸ
    0.08
    æĪĸèĢħåħ¶ä»ĸ
    0.08
    å¤įåĪ¶æĪĸ
    0.08
    Activations Density 0.195%

    No Known Activations