© 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. 19601
    Prev
    Next
    INDEX
    Explanations

    consumer products, tech, electronics, or issues

    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
    auj
    -0.06
    ments
    -0.06
    اÙĪ
    -0.06
    ждÑĥÑİ
    -0.06
    ä½Ĩä¸įéĻIJäºİ
    -0.06
    mates
    -0.06
    så
    -0.06
    warzys
    -0.06
    enta
    -0.06
    chaft
    -0.06
    POSITIVE LOGITS
    i
    0.08
    onomy
    0.07
    è±ļ
    0.06
    ´
    0.06
     Cant
    0.06
    idler
    0.06
    icy
    0.05
    å°Ķ
    0.05
    ers
    0.05
    ation
    0.05
    Activations Density 0.007%

    No Known Activations