© 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. 15720
    Prev
    Next
    INDEX
    Explanations

    transient intermediates or species

    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
    æ¸IJ
    -0.07
    é»ĺå¥ij
    -0.07
    egger
    -0.07
    è®©æĽ´å¤ļçļĦ
    -0.06
    relations
    -0.06
     Habitat
    -0.06
    ı
    -0.06
     Quan
    -0.06
    è§Ĥ
    -0.06
    è°ĥèĬĤ
    -0.06
    POSITIVE LOGITS
    ä¸ŃéĹ´ä½ĵ
    0.09
    æļĤæŶçļĦ
    0.08
    çŁŃæļĤ
    0.08
    çŁŃæļĤçļĦ
    0.08
    ä¸į稳
    0.08
    åĽĽå¤Ħ
    0.08
     fleeting
    0.08
     formed
    0.08
     momentarily
    0.08
    idio
    0.08
    Activations Density 0.008%

    No Known Activations