© 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. 20783
    Prev
    Next
    INDEX
    Explanations

    acrylated, lam, lated

    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
     Stade
    -0.07
    elier
    -0.07
    ÑĢÑij
    -0.06
    ืà¹Īà¸Ń
    -0.06
    æľīåij³
    -0.06
    解ä½ĵ
    -0.06
    çļĦæĸ°æĹ¶ä»£
    -0.06
    ÃŃda
    -0.06
     Dise
    -0.06
    èĬĤ
    -0.06
    POSITIVE LOGITS
    bens
    0.06
    log
    0.05
    uang
    0.05
    ikit
    0.05
    aml
    0.05
    åĩĨ
    0.05
     Bayesian
    0.05
    tte
    0.05
    agation
    0.05
    bn
    0.05
    Activations Density 0.008%

    No Known Activations