© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 14798
    Prev
    Next
    INDEX
    Explanations

    maturation, quality, properly

    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
    çļĦåĬĽåº¦
    -0.07
    endu
    -0.07
    俱ä¹IJéĥ¨
    -0.07
    uits
    -0.07
    大çĤ®
    -0.06
     ôn
    -0.06
    æ±ĩ
    -0.06
    åĪĨ管
    -0.06
     conseg
    -0.06
    /company
    -0.06
    POSITIVE LOGITS
    ä¿Ŀè¯ģåħ¶
    0.10
    使åħ¶
    0.10
    让åħ¶
    0.10
    å½ĵåħ¶
    0.09
    èĩªèº«çļĦ
    0.09
    åıĸæ¶Īåħ¶
    0.09
    è¦ģæ±Ĥåħ¶
    0.09
     Ñģвоей
    0.09
    ifecycle
    0.09
    çĶ±åħ¶
    0.08
    Activations Density 0.449%

    No Known Activations