© 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. 31098
    Prev
    Next
    INDEX
    Explanations

    we followed by a verb

    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
    orrent
    -0.09
    èµĦæĸĻæĺ¾ç¤º
    -0.08
    çĦ¶åIJİçĤ¹åĩ»
    -0.08
    åĪĴåĪĨ为
    -0.07
    æķ°æį®æĺ¾ç¤º
    -0.07
    СУ
    -0.07
    HashCode
    -0.07
    océ
    -0.07
    éĹ®éģĵ
    -0.07
    isa
    -0.07
    POSITIVE LOGITS
    å¾Ĺä¸Ĭ
    0.08
    ave
    0.08
    heet
    0.07
    ers
    0.07
    ï¸ı
    0.07
    £
    0.07
    乡çļĦ
    0.07
    ä¹İåħ¶
    0.07
    åħ¶çľŁå®ŀæĢ§
    0.07
    踵
    0.07
    Activations Density 0.055%

    No Known Activations