© 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. 21266
    Prev
    Next
    INDEX
    Explanations

    json objects with id

    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
    ness
    -0.09
    à§įত
    -0.07
    ly
    -0.07
    nya
    -0.06
    ship
    -0.06
    comed
    -0.06
    led
    -0.06
    NESS
    -0.06
    iblioth
    -0.06
    phant
    -0.06
    POSITIVE LOGITS
    érie
    0.06
    edes
    0.06
    æĶ¾åѦ
    0.06
    chester
    0.06
    ensively
    0.06
    esch
    0.06
    uxtap
    0.06
    es
    0.06
    /her
    0.05
    کارÛĮ
    0.05
    Activations Density 0.006%

    No Known Activations