© 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. 18603
    Prev
    Next
    INDEX
    Explanations

    decorative flag

    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
    less
    -0.06
    贯穿
    -0.05
    æĹłæĥħ
    -0.05
    Online
    -0.05
    åħ¨éĿ¢æ·±åĮĸæĶ¹éĿ©
    -0.05
    ÑĩаÑģÑĤ
    -0.05
    æľīèĩ´
    -0.05
     underground
    -0.05
    ly
    -0.05
     prominent
    -0.05
    POSITIVE LOGITS
     Edel
    0.07
    ä¿¡æģ¯è¿Ľè¡Į
    0.06
    æľīçĶ¨çļĦ
    0.06
    åı¯èĥ½å°±
    0.06
     useful
    0.06
    ç½¢äºĨ
    0.06
    zuki
    0.06
     wanted
    0.06
    iali
    0.06
    brands
    0.06
    Activations Density 0.056%

    No Known Activations