© 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. 20448
    Prev
    Next
    INDEX
    Explanations

    protect against threats

    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
    åıįä¹ĭ
    -0.06
    adox
    -0.06
     Arro
    -0.06
    oÄį
    -0.06
    ÙĨاÙħÙĩ
    -0.06
    iÃŁ
    -0.06
    åıįè¿ĩæĿ¥
    -0.06
    awat
    -0.06
    ojis
    -0.06
    oit
    -0.06
    POSITIVE LOGITS
    鲤
    0.06
    errer
    0.05
    2
    0.05
     bully
    0.05
    亮çļĦ
    0.05
    ings
    0.05
     adequately
    0.05
    æ±Ģ
    0.05
    ichtig
    0.05
    ages
    0.05
    Activations Density 0.008%

    No Known Activations