© 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. 19392
    Prev
    Next
    INDEX
    Explanations

    alternative

    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
    :\"
    -0.06
    owell
    -0.06
    ÃŃc
    -0.06
    anaan
    -0.06
    ähl
    -0.06
    åĪ·
    -0.06
    å°½å¿ĥ
    -0.06
    rach
    -0.06
    .\"
    -0.06
    ..'
    -0.06
    POSITIVE LOGITS
    word
    0.05
    å´İ
    0.05
    ä¾ĿåŃĺ
    0.05
    ither
    0.05
    åħ³
    0.05
    æ¶Īæģ¯
    0.05
     ÑģÑĥÑĤ
    0.05
    æĸ¯
    0.05
    ำ
    0.05
     سر
    0.05
    Activations Density 0.001%

    No Known Activations