© 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. 12835
    Prev
    Next
    INDEX
    Explanations

    out of sorts

    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
    æīĢ以ä»ĸ们
    -0.09
    çļĦèĥĮå½±
    -0.08
    æ¯ĶæĪij们
    -0.08
    æĪij们çľĭåĪ°
    -0.08
     theirs
    -0.08
     conosco
    -0.07
    ä»ĸ们çļĦ
    -0.07
     THEIR
    -0.07
    åIJijæĪij们
    -0.07
    çľĭå¾ĹåĩºæĿ¥
    -0.07
    POSITIVE LOGITS
    æĦŁè§īèĩªå·±
    0.12
     myself
    0.11
     feels
    0.10
    è¿Ļç§įæĦŁè§ī
    0.10
    åijĬè¯īèĩªå·±
    0.10
    çļĦæĦŁè§ī
    0.09
     feeling
    0.09
    çļĦèĩªå·±
    0.09
    åīįæīĢæľªæľīçļĦ
    0.09
    æĢĿ绪
    0.09
    Activations Density 1.085%

    No Known Activations