© 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. 19283
    Prev
    Next
    INDEX
    Explanations

    foreign language or garbled text

    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
    chal
    -0.05
    以任ä½ķ
    -0.05
     Death
    -0.05
    ths
    -0.05
     glac
    -0.05
     domin
    -0.05
    çon
    -0.05
    èIJ±
    -0.05
    uss
    -0.05
    ...
    -0.04
    POSITIVE LOGITS
    å®ŀåĬ¡
    0.07
     leider
    0.07
    ä¸Ģäºĭ
    0.06
    ubi
    0.06
    ECTOR
    0.06
    еÑģÑĤв
    0.06
    obil
    0.06
     fastest
    0.06
    вок
    0.06
    tics
    0.06
    Activations Density 0.014%

    No Known Activations