© 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. 29138
    Prev
    Next
    INDEX
    Explanations

    concluding phrases

    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
    ÙħاÙĨ
    -0.08
    utki
    -0.08
    atik
    -0.08
    ehren
    -0.07
    åħ¶ä¸Ńä¹ĭä¸Ģ
    -0.07
     замеÑģÑĤи
    -0.07
    atif
    -0.07
     ìķĦëĭĪê³ł
    -0.07
    ukah
    -0.07
    æĪij们æŃ£åľ¨
    -0.07
    POSITIVE LOGITS
     overall
    0.09
    è¶Ĭæĥ³
    0.08
    æĢ»çļĦ
    0.08
    overall
    0.08
    æķ´ä½ĵ
    0.07
     tot
    0.07
    æĥ³åĪ°è¿ĻéĩĮ
    0.07
     resulting
    0.07
    æķ´ä½ĵä¸Ĭ
    0.07
     resultant
    0.06
    Activations Density 0.005%

    No Known Activations