© 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. 30279
    Prev
    Next
    INDEX
    Explanations

    programme or car

    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
    æľįèį¯
    -0.07
    èµĸ以
    -0.07
    å°ıå¿ĥ
    -0.06
    æĹłåıį
    -0.06
    漩涡
    -0.06
    åIJı
    -0.06
    åĪĩéĻ¤æľ¯
    -0.06
    Forge
    -0.06
    æ´ŀå¯ŁåĬĽ
    -0.06
     uf
    -0.06
    POSITIVE LOGITS
     Nues
    0.08
    è§Ħå®ļ
    0.08
     vonat
    0.08
    è§Ħå®ļäºĨ
    0.08
    è¦ģæ±Ĥåľ¨
    0.08
    æ°ijçĶ¨
    0.08
    idas
    0.08
    entr
    0.08
     Usai
    0.08
    æĽ´æĸ°äºĨ
    0.08
    Activations Density 0.004%

    No Known Activations