© 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. 19579
    Prev
    Next
    INDEX
    Explanations

    seasonal variation and adjustment

    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
    é«ĺå¯Ĩ度
    -0.07
     opt
    -0.06
    tter
    -0.06
    ichte
    -0.06
    eya
    -0.06
    pum
    -0.06
    iller
    -0.06
    çĿĢåĬĽæīĵéĢł
    -0.06
    é«ĺå¯Ĩ
    -0.06
     recieved
    -0.06
    POSITIVE LOGITS
    ç§ī
    0.06
     inherent
    0.06
     attributable
    0.05
     factor
    0.05
    æĪIJåĪĨ
    0.05
    åĽłç´ł
    0.05
    اÙĨÙĩ
    0.05
    ursa
    0.05
     factors
    0.05
     part
    0.05
    Activations Density 0.015%

    No Known Activations