© 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. 63829
    Prev
    Next
    INDEX
    Explanations

    maybe perhaps whether

    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
     presumably
    -0.09
    retty
    -0.08
    oine
    -0.08
     Terrace
    -0.07
    ä»ĸ表示
    -0.07
    olley
    -0.07
     probably
    -0.07
     essentially
    -0.07
     apparently
    -0.07
    ottes
    -0.07
    POSITIVE LOGITS
    æĬķèµĦæĪĸ
    0.10
    éĶĻ误æĪĸ
    0.09
    å·¥ä½ľæĪĸ
    0.09
    æĸĩ件æĪĸ
    0.09
    æŃ£åľ¨
    0.09
    åıij表æĪĸ
    0.08
    çĶ¨äºİæ²»çĸĹ
    0.08
    å¤įåĪ¶æĪĸ
    0.08
    :start
    0.08
    å°¤
    0.08
    Activations Density 0.035%

    No Known Activations