© 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. 42058
    Prev
    Next
    INDEX
    Explanations

    upward or downward direction

    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
    ühl
    -0.09
    ר×ĺ
    -0.08
    ÙĦÙĬت
    -0.07
     Tough
    -0.07
    æĻ¤
    -0.07
    æĹ¥åĪ¶
    -0.07
    hausen
    -0.07
     epidemi
    -0.07
    åį«çĶŁç»Ħç»ĩ
    -0.07
    åħ´éļĨ
    -0.07
    POSITIVE LOGITS
    åIJijä¸ĭ
    0.10
     upward
    0.10
    åIJijä¸Ĭ
    0.10
     downward
    0.10
    åIJijä¸ĬçļĦ
    0.09
    æµģåIJij
    0.09
     toward
    0.09
    ä¹ĭåĬ¿
    0.09
    /down
    0.09
    å·ħ
    0.09
    Activations Density 0.003%

    No Known Activations