© 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. 20565
    Prev
    Next
    INDEX
    Explanations

    non-english characters

    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
     intim
    -0.06
    çļĦæĸ¹æ¡Ī
    -0.06
    berg
    -0.06
    æĪijä¸įæķ¢
    -0.06
    å¹³éĺ³
    -0.06
    inkin
    -0.06
    ãĤĴåºĥ
    -0.05
    alap
    -0.05
    ivel
    -0.05
    weit
    -0.05
    POSITIVE LOGITS
    taget
    0.06
    çĸı
    0.06
    åĩ
    0.06
    ¡
    0.06
    èµĭ
    0.06
    öm
    0.05
    éĿ¶
    0.05
    æĬļ
    0.05
    纳
    0.05
     Pur
    0.05
    Activations Density 0.005%

    No Known Activations