© 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. 18922
    Prev
    Next
    INDEX
    Explanations

    or otherwise

    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
    mals
    -0.06
    éĩįäºİ
    -0.06
    æĥħçļĦ
    -0.06
    ä¸Ģ次
    -0.05
    æĪĸ缴æİ¥
    -0.05
    å¹´åħ¨åĽ½
    -0.05
    ters
    -0.05
    æĥħ
    -0.05
    è¨Ģä¹ĭ
    -0.05
     valid
    -0.05
    POSITIVE LOGITS
    çais
    0.06
    oken
    0.06
    osotros
    0.05
    jos
    0.05
    issy
    0.05
    else
    0.05
    žen
    0.05
    åıįæŃ£
    0.05
    erken
    0.05
    orks
    0.05
    Activations Density 0.041%

    No Known Activations