© 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. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 20597
    Prev
    Next
    INDEX
    Explanations

    corporations and companies ending in Corp or Co

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    åĿ·
    -0.06
     Tän
    -0.06
    æİ¥åĪ°äºĨ
    -0.06
    设为é¦ĸ页
    -0.06
    ä¾ĽæĩīéıĪ
    -0.06
    izion
    -0.05
     kommende
    -0.05
    Äĥr
    -0.05
     Estud
    -0.05
    tsy
    -0.05
    POSITIVE LOGITS
    å®ļ
    0.06
     Hé
    0.06
    å·¥
    0.06
    ä¸Ģåī¯
    0.06
    æŁIJç§į
    0.05
    使èĩªå·±
    0.05
    ами
    0.05
    书
    0.05
     reign
    0.05
    èĭ¥æľī
    0.05
    Activations Density 0.007%

    No Known Activations