© 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. 20702
    Prev
    Next
    INDEX
    Explanations

    `"` or `"` followed by name/href/size

    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
    xic
    -0.06
     Eis
    -0.05
    ib
    -0.05
    -
    -0.05
    ÅĤam
    -0.05
    sig
    -0.05
    èĮ¶é¦Ĩ
    -0.05
    idar
    -0.05
    以æ±Ĥ
    -0.05
     sums
    -0.04
    POSITIVE LOGITS
    oft
    0.08
    ulton
    0.07
    apon
    0.07
    让æĤ¨çļĦ
    0.06
     lạ
    0.06
    ÙĥرÙĪÙĨ
    0.06
    /inc
    0.06
    bject
    0.06
    fsp
    0.06
    为æĤ¨çļĦ
    0.06
    Activations Density 0.011%

    No Known Activations