© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 21998
    Prev
    Next
    INDEX
    Explanations

    Business

    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
    å¿ħéľĢåĵģ
    -0.06
    ç»Ĩå¿ĥçļĦ
    -0.06
    zier
    -0.05
    .pitch
    -0.05
    itable
    -0.05
     kê
    -0.05
    اÙĨات
    -0.05
    åħ±äº§ä¸»ä¹ī
    -0.05
    ife
    -0.05
    AIT
    -0.05
    POSITIVE LOGITS
    ilage
    0.06
    olda
    0.06
    cus
    0.06
    åĽ½äº§
    0.06
    大ä¹ī
    0.05
     handguns
    0.05
     ÙģÙĪت
    0.05
    dann
    0.05
    红
    0.05
     prens
    0.05
    Activations Density 0.017%

    No Known Activations