© 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. 17131
    Prev
    Next
    INDEX
    Explanations

    code language keywords

    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
    éªģ
    -0.06
    æĪĺ线
    -0.05
    verts
    -0.05
    angeb
    -0.05
    (es
    -0.05
     clad
    -0.05
    /do
    -0.05
     alo
    -0.05
    ickle
    -0.05
    marks
    -0.05
    POSITIVE LOGITS
    خر
    0.05
    çļĦçIJĨ念
    0.05
    åĹ¡
    0.05
    çĿĽ
    0.05
     urn
    0.05
     ê±´
    0.05
    å¿¿
    0.05
     gospel
    0.05
    æĸĩæķĻ
    0.05
    çIJĨ念
    0.05
    Activations Density 0.079%

    No Known Activations