© 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. 19492
    Prev
    Next
    INDEX
    Explanations

    tube, coil, taco, acid, alert, worker

    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
    бÑĥдÑĮÑĤе
    -0.05
    ÄĽj
    -0.05
     بÙĩ
    -0.05
    ÙħÙĪÙĨ
    -0.05
    reste
    -0.05
    æī©å±ķèµĦæĸĻ
    -0.05
    porti
    -0.05
    UTO
    -0.05
    æĸ°éĻĪ代谢
    -0.05
    Eb
    -0.05
    POSITIVE LOGITS
    ÂŃt
    0.07
    anna
    0.06
    ces
    0.06
    ieszcz
    0.06
    -r
    0.06
    istically
    0.06
    广åijĬå®£ä¼ł
    0.06
    omas
    0.05
    çĶ¨åħ·
    0.05
    oi
    0.05
    Activations Density 0.260%

    No Known Activations