© 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. 4369
    Prev
    Next
    INDEX
    Explanations

    `product` or `returns`

    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
     Mã
    -0.08
    ccc
    -0.07
    æĹłäºĭ
    -0.07
    Mã
    -0.07
    ä¸įè§ī
    -0.07
    ึà¹Īà¸ĩ
    -0.07
    XYZ
    -0.07
    ajara
    -0.07
    ops
    -0.07
    è¾ĥ好
    -0.07
    POSITIVE LOGITS
    åºĶåħĪ
    0.08
    çĦ¶åIJİçĤ¹åĩ»
    0.07
    çĦ¶åIJİæĬĬ
    0.07
    çĦ¶åIJİå°Ĩ
    0.07
     deserving
    0.07
    å¿ħé¡»åħĪ
    0.07
    æĺ¯åħĪ
    0.07
    çĦ¶åIJİå°±
    0.07
    çĦ¶åIJİåĨį
    0.06
     puis
    0.06
    Activations Density 0.002%

    No Known Activations