© 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. 18862
    Prev
    Next
    INDEX
    Explanations

    syntax questions

    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
    ترÛĮÙĨ
    -0.06
    -headed
    -0.06
    erber
    -0.05
    ashing
    -0.05
    éļ¾çļĦ
    -0.05
    çĦ¶
    -0.05
    -
    -0.04
    &
    -0.04
    بر
    -0.04
    headed
    -0.04
    POSITIVE LOGITS
    iewicz
    0.08
    (es
    0.07
    ioned
    0.07
    ÙĬØ·
    0.07
    е
    0.07
    á»ıa
    0.07
    hluk
    0.07
    esistenza
    0.07
    eshire
    0.07
    aday
    0.07
    Activations Density 0.009%

    No Known Activations