© 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. 20334
    Prev
    Next
    INDEX
    Explanations

    items that are followed by descriptive words

    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
    olos
    -0.06
     cÃŃ
    -0.06
     lang
    -0.06
    inales
    -0.06
    idon
    -0.06
     aspire
    -0.06
     ör
    -0.06
    )))),
    -0.06
    对åħ¶ä»ĸ
    -0.06
     curt
    -0.05
    POSITIVE LOGITS
    ÑĥкÑĢа
    0.05
    lož
    0.05
    iko
    0.05
    Party
    0.05
     nejen
    0.05
    ouvr
    0.05
    oco
    0.05
    oris
    0.04
    æĿ¥ä¹ĭ
    0.04
    he
    0.04
    Activations Density 0.017%

    No Known Activations