© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 19854
    Prev
    Next
    INDEX
    Explanations

    list structures

    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
    lags
    -0.06
    éĩįè¦ģæĢ§
    -0.06
    pire
    -0.06
    mie
    -0.06
    hamdulillah
    -0.06
    ÙħÙĦØ©
    -0.06
    ç¡
    -0.06
    riel
    -0.06
     cad
    -0.05
    çłĶ究åĴĮ
    -0.05
    POSITIVE LOGITS
    edale
    0.07
    ed
    0.07
    ward
    0.06
    aped
    0.06
    好å¿ĥ
    0.06
    θε
    0.05
    å½¢
    0.05
    -scalable
    0.05
     behalf
    0.05
    ä¸Ģä¸ĭåIJ§
    0.05
    Activations Density 0.003%

    No Known Activations