© 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. 20078
    Prev
    Next
    INDEX
    Explanations

    hidden items and places

    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
    åıĬåħ¶åºĶçĶ¨
    -0.07
    åıĬåºĶçĶ¨
    -0.06
     vaz
    -0.06
    Effect
    -0.06
    ä¸İåºĶçĶ¨
    -0.05
     spilled
    -0.05
    á»ĢN
    -0.05
    czyn
    -0.05
    brig
    -0.05
    æĹ©çĤ¹
    -0.05
    POSITIVE LOGITS
    åĴĮè°IJ
    0.05
     Satz
    0.05
    hidden
    0.05
    éļIJèĹıçĿĢ
    0.05
     carefully
    0.05
     resilient
    0.05
    å¯ĵ
    0.05
    åĪģ
    0.05
    Ñı
    0.05
    ipe
    0.05
    Activations Density 0.019%

    No Known Activations