© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 21249
    Prev
    Next
    INDEX
    Explanations

    please, advise, help

    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
    è²
    -0.06
    immy
    -0.06
    à¹Ģà¸Ľà¸£
    -0.06
    odore
    -0.06
    º
    -0.05
    zny
    -0.05
    çļĦä¿Ŀéļľ
    -0.05
    enam
    -0.05
    äºĨ
    -0.05
    دÙĪÙĨ
    -0.05
    POSITIVE LOGITS
    ivial
    0.07
    warzys
    0.07
    shire
    0.06
    cmb
    0.06
    sWith
    0.06
    swith
    0.06
    rk
    0.05
    ó
    0.05
    nier
    0.05
     rãi
    0.05
    Activations Density 0.002%

    No Known Activations