© 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. 21289
    Prev
    Next
    INDEX
    Explanations

    2D

    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
    shot
    -0.06
    ey
    -0.06
    eye
    -0.06
    çijĻ
    -0.06
    åºĵéĩĮ
    -0.05
    é«ĺå¯Ĩ度
    -0.05
    çĿĽ
    -0.05
    лк
    -0.05
    end
    -0.05
    ima
    -0.05
    POSITIVE LOGITS
    شر
    0.06
    æĸī
    0.06
    iminal
    0.06
    oard
    0.06
    ardy
    0.06
    صÙģ
    0.06
    iterr
    0.06
    kraine
    0.05
     Nicholson
    0.05
    èĪŁ
    0.05
    Activations Density 0.009%

    No Known Activations