© 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. 20772
    Prev
    Next
    INDEX
    Explanations

    syndrome

    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
    alls
    -0.06
    åĬ¡
    -0.06
    iance
    -0.06
     Blanch
    -0.06
    ÑĩинÑĭ
    -0.06
    alling
    -0.06
    rop
    -0.06
    ationally
    -0.06
    /non
    -0.05
    ä¸įåĬ¨
    -0.05
    POSITIVE LOGITS
    ed
    0.07
    apple
    0.06
     damit
    0.06
    img
    0.06
    éĻħ
    0.06
     wünsche
    0.06
    ful
    0.05
    igh
    0.05
    اÙģÙĦØ©
    0.05
    ual
    0.05
    Activations Density 0.014%

    No Known Activations