© 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. 11725
    Prev
    Next
    INDEX
    Explanations

    faster, slower, higher, better compared to

    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
    å¤ĩ好
    -0.07
    åĬªåĬĽä¸ĭ
    -0.07
    пл
    -0.07
    quartered
    -0.06
    çĿ¹
    -0.06
    umentos
    -0.06
    大大æıIJé«ĺäºĨ
    -0.06
    æŀĹä¸Ń
    -0.06
     Lug
    -0.06
    è¶ĬãģĹ
    -0.06
    POSITIVE LOGITS
     than
    0.30
    than
    0.24
    _than
    0.22
     THAN
    0.21
    -than
    0.20
    Than
    0.20
     kuin
    0.19
     Than
    0.18
     niż
    0.17
     než
    0.17
    Activations Density 0.256%

    No Known Activations