© 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. 20716
    Prev
    Next
    INDEX
    Explanations

    dividing into segments, subsets, regions, sections, pieces, groups, parts

    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
    sud
    -0.06
    éĥ¨åĪĨç»ĦæĪIJ
    -0.05
    åįĺ
    -0.05
    ergebnisse
    -0.05
    çľ©
    -0.05
    æĵħéķ¿çļĦ
    -0.05
    端çĿĢ
    -0.05
    å¼ĺ
    -0.05
    hle
    -0.05
    æĪIJ
    -0.05
    POSITIVE LOGITS
    anders
    0.06
    ander
    0.06
    gaan
    0.06
    row
    0.06
    antas
    0.06
    оби
    0.06
    ded
    0.05
    urg
    0.05
    åIJijåħ¶
    0.05
    anner
    0.05
    Activations Density 0.022%

    No Known Activations