© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 21219
    Prev
    Next
    INDEX
    Explanations

    soft tissue

    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
    ated
    -0.07
    oire
    -0.07
    Ùĩ
    -0.07
    ATED
    -0.06
    ми
    -0.06
    аÑĤоÑĢа
    -0.06
    ãģªãĤīãģļ
    -0.06
    ìĦľ
    -0.06
    ator
    -0.06
    er
    -0.06
    POSITIVE LOGITS
    ness
    0.09
    enschaft
    0.07
    iloc
    0.07
    ampton
    0.07
    iero
    0.06
    æĿ¾
    0.06
    errs
    0.06
    ibilities
    0.06
    主ä¹ī
    0.06
    uncul
    0.06
    Activations Density 0.004%

    No Known Activations