© 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. 18229
    Prev
    Next
    INDEX
    Explanations

    lists, levels, sector, elements, process

    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
    omini
    -0.08
    kout
    -0.07
    ?):
    -0.07
    kien
    -0.06
    ئÙħ
    -0.06
    antina
    -0.06
    !:
    -0.06
    éķ¿æĪIJ
    -0.06
    fas
    -0.06
    kland
    -0.06
    POSITIVE LOGITS
    ÛĮس
    0.05
    è¿Ļ两
    0.05
    ct
    0.05
    usto
    0.05
    ust
    0.05
     dialect
    0.05
    è´Ń
    0.05
    °
    0.05
    ime
    0.05
     extra
    0.05
    Activations Density 0.009%

    No Known Activations