© 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. 2824
    Prev
    Next
    INDEX
    Explanations

    thanks for the answer

    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
    kaw
    -0.07
    æĬĬè¿ĻäºĽ
    -0.06
     Kav
    -0.06
    andler
    -0.06
    izr
    -0.06
    åı¦ä¸Ģè¾¹
    -0.06
    utum
    -0.06
    occupation
    -0.06
    ¾
    -0.06
    κÏĮ
    -0.06
    POSITIVE LOGITS
    å§ĭèĩ³
    0.08
    ahuan
    0.08
    èī²åĪĹ
    0.08
    aik
    0.07
    ujet
    0.07
    å¦ĥ
    0.07
    abis
    0.07
    è¿ĶåĽŀåĪĹ表
    0.07
    幸è¿IJçļĦæĺ¯
    0.07
    çļĦåħīèį£
    0.07
    Activations Density 0.692%

    No Known Activations