© 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. 41862
    Prev
    Next
    INDEX
    Explanations

    RPG tree, completed books, journals, UDP connections, map, grass, accommodations, asymmetric encryption, account, striped T

    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
    èĻ½çĦ¶ä¸įæĺ¯
    -0.07
    even
    -0.07
     even
    -0.07
    çĶļèĢħ
    -0.07
    zem
    -0.07
    æ·ĩ
    -0.07
    umen
    -0.06
    åĪ»éª¨
    -0.06
    uld
    -0.06
    angnya
    -0.06
    POSITIVE LOGITS
    éĤ£ä¹Īç®Ģåįķ
    0.13
    è¿Ļä¹Īç®Ģåįķ
    0.10
    èĢĮå·²
    0.09
    æŁIJ人
    0.09
    ç®Ģåįķåľ°
    0.09
    å°±è¡ĮäºĨ
    0.09
     semata
    0.09
    ç®ĢåįķçļĦ
    0.08
    æŁIJä¸Ģ个
    0.08
    ä¹°ä¹°
    0.08
    Activations Density 0.269%

    No Known Activations