© 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. 19371
    Prev
    Next
    INDEX
    Explanations

    answer

    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
    گاÙĩ
    -0.06
    гÑĢе
    -0.05
    ely
    -0.05
    jÅ¡ÃŃm
    -0.05
    رÙĪ
    -0.05
    lys
    -0.05
    çļĦè¿Ļç§į
    -0.05
    ừa
    -0.05
    åĴĮåŁ¹åħ»
    -0.05
    åĸ·æ¼Ĩ
    -0.05
    POSITIVE LOGITS
    ë²Į
    0.06
    ниÑĨ
    0.06
    மி
    0.06
    idora
    0.05
    ä¸īäºĶ
    0.05
    мили
    0.05
    滩
    0.05
    åľ¨æѤ
    0.05
    chenk
    0.05
    cks
    0.05
    Activations Density 0.007%

    No Known Activations