© 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. 18289
    Prev
    Next
    INDEX
    Explanations

    table schema definitions

    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
    ór
    -0.06
    alen
    -0.06
    éħª
    -0.06
    iedad
    -0.06
    azza
    -0.05
    ANDOM
    -0.05
    èĶ¼
    -0.05
    ália
    -0.05
    å¸ļ
    -0.05
    ÑģлÑĮ
    -0.05
    POSITIVE LOGITS
    ves
    0.06
     ditem
    0.05
    verts
    0.05
    ks
    0.05
     Reis
    0.05
    èĭĹ
    0.05
    å®ĺæĸ¹åįļ客
    0.05
    [âĢ¦
    0.05
    .pub
    0.05
     sos
    0.05
    Activations Density 0.027%

    No Known Activations