© 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. 42494
    Prev
    Next
    INDEX
    Explanations

    itself, themselves, himself

    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
    ibel
    -0.08
    vegli
    -0.08
    åħ±åIJĮè¿ĽæŃ¥
    -0.08
    ä¸ŃçļĦæīĢæľī
    -0.08
    åħ±åIJĮåĬªåĬĽ
    -0.08
    æŀľçĦ¶
    -0.07
    ôm
    -0.07
    羣æŃ£æĬĬ
    -0.07
    è·Łåħļèµ°
    -0.07
    æŀľçľŁ
    -0.07
    POSITIVE LOGITS
    æľ¬èº«
    0.17
     itself
    0.16
    æľ¬èº«çļĦ
    0.12
     sendiri
    0.11
    æľ¬èº«å°±æĺ¯
    0.11
    æľ¬èº«å°±
    0.11
     themselves
    0.10
     Ñģебе
    0.09
     himself
    0.09
     magát
    0.09
    Activations Density 0.088%

    No Known Activations