© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19522
    Prev
    Next
    INDEX
    Explanations

    are not

    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
    klub
    -0.06
    adel
    -0.05
    ways
    -0.05
    ات
    -0.05
    ald
    -0.05
    iclet
    -0.05
    lig
    -0.05
    liz
    -0.05
    lus
    -0.05
    ondi
    -0.05
    POSITIVE LOGITS
    казÑĭваеÑĤÑģÑı
    0.06
    å°Ĩè¾¾
    0.06
    unce
    0.06
    åĮº
    0.06
    UNS
    0.05
    ibra
    0.05
    fy
    0.05
    erber
    0.05
    èĿĩ
    0.05
    shore
    0.05
    Activations Density 0.003%

    No Known Activations