© 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. 19887
    Prev
    Next
    INDEX
    Explanations

    required collected

    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
    ãģ¬
    -0.07
    ä¸įèĥ½ä½ľä¸º
    -0.07
     Cannot
    -0.06
    ç¥ŀä¹ĭ
    -0.06
    ÙĬع
    -0.06
    Detailed
    -0.06
    é«ĺéĢŁå¢ŀéķ¿
    -0.06
    isper
    -0.06
    æľªåıĸå¾Ĺ
    -0.06
     inability
    -0.06
    POSITIVE LOGITS
    ä½ķå¿ħ
    0.06
     des
    0.05
     i
    0.05
    并ä¸įéľĢè¦ģ
    0.05
     Trim
    0.05
    Trim
    0.05
    æŃ¢
    0.05
    æłĩ
    0.05
     /
    0.04
     presence
    0.04
    Activations Density 0.069%

    No Known Activations