© 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. 16955
    Prev
    Next
    INDEX
    Explanations

    .dto, .Domain, or class names

    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
    éĴ®
    -0.07
    ouz
    -0.05
    à¤Ĥà¤ķ
    -0.05
    个ä½ĵ
    -0.05
    é¢ĨåŁŁä¸Ń
    -0.05
    弧
    -0.05
    ãĤĴçĻº
    -0.05
    à°µà±ģ
    -0.05
     impart
    -0.05
    illis
    -0.05
    POSITIVE LOGITS
    å®ĺ
    0.07
     destination
    0.06
     spaces
    0.06
    ainer
    0.06
    æĪ
    0.05
    æ»ŀçķĻ
    0.05
    Destination
    0.05
    enger
    0.05
    fal
    0.05
    人ä¸Ģ
    0.05
    Activations Density 0.157%

    No Known Activations