© 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. 19129
    Prev
    Next
    INDEX
    Explanations

    picking from sets

    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
     apres
    -0.05
    iap
    -0.05
     del
    -0.04
    (s
    -0.04
    ÙħÙĬÙĦ
    -0.04
    ÙħÙħ
    -0.04
     trop
    -0.04
    erial
    -0.04
    夥
    -0.04
     af
    -0.04
    POSITIVE LOGITS
    atika
    0.07
    -elements
    0.07
     redak
    0.06
    akwa
    0.06
    scha
    0.06
    arges
    0.06
     Jat
    0.06
    алан
    0.06
    engg
    0.06
    tock
    0.06
    Activations Density 0.023%

    No Known Activations