© 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. 21969
    Prev
    Next
    INDEX
    Explanations

    tensile strength and mechanical properties

    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
    /fa
    -0.06
    FO
    -0.06
    trop
    -0.06
    åĩĢ
    -0.05
     unn
    -0.05
    çĶŁæºIJ
    -0.05
     disf
    -0.05
    涤
    -0.05
    attr
    -0.05
    nat
    -0.05
    POSITIVE LOGITS
     stress
    0.08
     stresses
    0.07
    stress
    0.07
     Stress
    0.07
    é¢ĦåºĶåĬĽ
    0.06
    isses
    0.06
    åºĶåĬĽ
    0.06
    ä¸ļä½Ļ
    0.06
     tendon
    0.06
     endurance
    0.06
    Activations Density 0.055%

    No Known Activations